{"source":"AIMap","schema":"benchmark/v1","updated":"2026-10-22","benchmark":{"id":"mmlu-pro","name":"MMLU-Pro","category":"knowledge","unit":"%","higherIsBetter":true,"status":"active","sources":["mmlupro"],"primaryVariant":"overall","url":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","year":2024,"desc":{"en":"Harder successor to MMLU: about 12,000 reasoning-heavy questions in 14 disciplines with 10 answer options.","zh-hans":"MMLU 的加难版：约 1.2 万道偏推理的题，14 个学科，每题 10 个选项。"},"measures":{"en":"Knowledge plus reasoning, usually with chain-of-thought.","zh-hans":"知识加推理，通常使用思维链。"},"limits":{"en":"The official leaderboard mixes TIGER-Lab runs with self-reported numbers; we label each row.","zh-hans":"官方榜混合了 TIGER-Lab 自测和厂商自报分数，本站逐条标注。"},"contamination":"medium","contaminationNote":{"en":"Public test set since 2024.","zh-hans":"测试集自 2024 年公开。"},"stats":{"results":247,"models":243,"latest":"2026-03-11","bySourceType":{"official":114,"vendor":133}}},"sources":[{"id":"mmlupro","name":"MMLU-Pro leaderboard (TIGER-Lab)","license":"Apache-2.0 (dataset)","policy":"open","attribution":"TIGER-Lab, MMLU-Pro leaderboard","site":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro"}],"results":[{"model":"gemini-3-1-pro","modelName":"Gemini 3.1 Pro","provider":"Google","rawName":"Gemini-3.1-Pro","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":91.16,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-3-pro","modelName":"Gemini 3 Pro","provider":"Google","rawName":"Gemini-3-Pro(11/25)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":90.1,"unit":"%","rank":2,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-o1","modelName":"GPT-o1","provider":"OpenAI","rawName":"GPT-o1","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":89.3,"unit":"%","rank":3,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-4-6-opus","modelName":"Claude-4.6-Opus(Thinking)","provider":"Anthropic","rawName":"Claude-4.6-Opus(Thinking)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":89.1,"unit":"%","rank":4,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-3-flash-12-25","modelName":"25)","provider":"Google","rawName":"Gemini-3-Flash(12/25)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":88.6,"unit":"%","rank":5,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"minimax-m2-1","modelName":"MiniMax-M2.1","provider":"MiniMax","rawName":"MiniMax-M2.1","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 229B","score":88,"unit":"%","rank":6,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-5-397b-a17b","modelName":"Qwen3.5 397B-A17B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5-397B-A17B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 397B","score":87.8,"unit":"%","rank":7,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"seed2-0-lite","modelName":"Seed2.0-Lite","provider":"ByteDance","rawName":"Seed2.0-Lite","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":87.7,"unit":"%","rank":8,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-5-4","modelName":"GPT-5.4","provider":"OpenAI","rawName":"GPT-5.4","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":87.5,"unit":"%","rank":9,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-5-2","modelName":"GPT-5.2","provider":"OpenAI","rawName":"GPT-5.2","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":87.4,"unit":"%","rank":10,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-4-5-sonnet","modelName":"Claude-4.5-Sonnet(Thinking)","provider":"Anthropic","rawName":"Claude-4.5-Sonnet(Thinking)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":87.4,"unit":"%","rank":10,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-4-opus","modelName":"claude-4-opus","provider":"Anthropic","rawName":"Claude-4-Opus-Thinking","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":87.3,"unit":"%","rank":12,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-4-5-opus","modelName":"claude-4-5-opus","provider":"Anthropic","rawName":"Claude-4.5-Opus(Thinking)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":87.3,"unit":"%","rank":12,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-4-6-sonnet","modelName":"Claude-4.6-Sonnet(Thinking)","provider":"Anthropic","rawName":"Claude-4.6-Sonnet(Thinking)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":87.3,"unit":"%","rank":12,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"hunyuan-t1","modelName":"Hunyuan-T1","provider":"Tencent","rawName":"Hunyuan-T1","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 389B","score":87.2,"unit":"%","rank":15,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-5","modelName":"GPT-5","provider":"OpenAI","rawName":"GPT-5(high)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":87.1,"unit":"%","rank":16,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"k2-5-1t-a32b","modelName":"K2.5-1T-A32B","provider":null,"rawName":"K2.5-1T-A32B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 1000B","score":87.1,"unit":"%","rank":16,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"seed-thinking-v1-5","modelName":"Seed-Thinking-v1.5","provider":"ByteDance","rawName":"Seed-Thinking-v1.5","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 200B","score":87,"unit":"%","rank":18,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"grok-4","modelName":"Grok 4","provider":"xAI","rawName":"Grok-4","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":87,"unit":"%","rank":18,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"seed2-0-pro","modelName":"Seed2.0-Pro","provider":"ByteDance","rawName":"Seed2.0-Pro","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":87,"unit":"%","rank":18,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-5-122b-a10b","modelName":"Qwen3.5-122B-A10B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5-122B-A10B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 122B","score":86.7,"unit":"%","rank":21,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"seed1-6","modelName":"Seed1.6-Thinking","provider":"ByteDance","rawName":"Seed1.6-Thinking","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 200B","score":86.6,"unit":"%","rank":22,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"seed1-6-base","modelName":"Seed1.6-Base","provider":"ByteDance","rawName":"Seed1.6-Base","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 200B","score":86.6,"unit":"%","rank":22,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"seed1-6-ada","modelName":"Seed1.6-Ada-Thinking","provider":"ByteDance","rawName":"Seed1.6-Ada-Thinking","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 200B","score":86.4,"unit":"%","rank":24,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-5-1","modelName":"GPT-5.1","provider":"OpenAI","rawName":"GPT-5.1","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":86.4,"unit":"%","rank":24,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-3-1-flash-lite-preview","modelName":"Gemini-3.1-Flash-Lite-Preview","provider":"Google","rawName":"Gemini-3.1-Flash-Lite-Preview","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":86.2,"unit":"%","rank":26,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-4-5","modelName":"GPT-4.5","provider":"OpenAI","rawName":"GPT-4.5","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":86.1,"unit":"%","rank":27,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-5-27b","modelName":"Qwen3.5-27B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5-27B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 27B","score":86.1,"unit":"%","rank":27,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-2-5-pro-jun-2025","modelName":"Gemini 2.5 Pro (Jun 2025)","provider":"Google","rawName":"Gemini-2.5-Pro","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":86,"unit":"%","rank":29,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"glm-5","modelName":"GLM-5","provider":"Zhipu AI (Z.ai)","rawName":"GLM-5","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 754B","score":86,"unit":"%","rank":29,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-max","modelName":"Qwen3-Max","provider":"Alibaba (Qwen)","rawName":"Qwen3-Max-Thinking","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":85.7,"unit":"%","rank":31,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-5-35b-a3b","modelName":"Qwen3.5-35B-A3B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5-35B-A3B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 35B","score":85.3,"unit":"%","rank":32,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-o3","modelName":"GPT-o3-high","provider":"OpenAI","rawName":"GPT-o3-high","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":85,"unit":"%","rank":33,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-v3-2","modelName":"DeepSeek-V3.2","provider":"DeepSeek","rawName":"DeepSeek-V3.2-Thinking","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 685B","score":85,"unit":"%","rank":33,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-v3-1","modelName":"DeepSeek-V3.1-Thinking","provider":"DeepSeek","rawName":"DeepSeek-V3.1-Thinking","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 681B","score":84.8,"unit":"%","rank":35,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"glm-4-5","modelName":"GLM-4.5","provider":"Zhipu AI (Z.ai)","rawName":"GLM-4.5","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 355B","score":84.6,"unit":"%","rank":36,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-2-5-pro-mar-2025","modelName":"Gemini 2.5 Pro (Mar 2025)","provider":"Google","rawName":"Gemini-2.5-Pro-Exp-03-25","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":84.52,"unit":"%","rank":37,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-235b-a22b-thinking-jul-2025","modelName":"Qwen3-235B-A22B-Thinking (Jul 2025)","provider":"Alibaba (Qwen)","rawName":"Qwen3-235B-A22B-Thinking-2507","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 235B","score":84.5,"unit":"%","rank":38,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"grok-4-1-fast","modelName":"Grok 4.1 fast","provider":"xAI","rawName":"Grok-4.1-Fast(Reasoning)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":84.2,"unit":"%","rank":39,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-r1","modelName":"DeepSeek-R1","provider":"DeepSeek","rawName":"DeepSeek-R1","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 671B","score":84,"unit":"%","rank":40,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-3-7-sonnet","modelName":"Claude 3.7 Sonnet","provider":"Anthropic","rawName":"Claude-3.7-Sonnet-Thinking","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":84,"unit":"%","rank":40,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-4-sonnet","modelName":"claude-4-sonnet","provider":"Anthropic","rawName":"Claude-4-Sonnet","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":83.7,"unit":"%","rank":42,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-v3-1-nonthinking","modelName":"DeepSeek-V3.1-NonThinking","provider":"DeepSeek","rawName":"DeepSeek-V3.1-NonThinking","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 671B","score":83.7,"unit":"%","rank":42,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"seed2-0-mini","modelName":"Seed2.0-Mini","provider":"ByteDance","rawName":"Seed2.0-Mini","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":83.6,"unit":"%","rank":44,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"intern-s1","modelName":"Intern-S1","provider":null,"rawName":"Intern-S1","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 235B","score":83.5,"unit":"%","rank":45,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-r1-may-2025","modelName":"DeepSeek-R1 (May 2025)","provider":"DeepSeek","rawName":"DeepSeek-R1-0528","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 671B","score":83.4,"unit":"%","rank":46,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"grok-3-mini","modelName":"Grok-3 mini","provider":"xAI","rawName":"Grok-3-mini","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":83,"unit":"%","rank":47,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-4-mini","modelName":"GPT-4-mini (high)","provider":"OpenAI","rawName":"GPT-4-mini (high)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":83,"unit":"%","rank":47,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-235b-a22b-instruct-jul-2025","modelName":"Qwen3-235B-A22B-Instruct (Jul 2025)","provider":"Alibaba (Qwen)","rawName":"Qwen3-235B-A22B-Instruct-2507","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 235B","score":83,"unit":"%","rank":47,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama4-behemoth","modelName":"Llama4-Behemoth","provider":"Meta","rawName":"Llama4-Behemoth","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 2000B","score":82.8,"unit":"%","rank":50,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"seed-oss-36b-instruct","modelName":"seed-oss-36b-instruct","provider":"ByteDance","rawName":"Seed-OSS-36B-Instruct","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 36B","score":82.7,"unit":"%","rank":51,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"longcat-flash-chat","modelName":"LongCat-Flash-Chat","provider":"Meituan","rawName":"LongCat-Flash-Chat","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 560B","score":82.7,"unit":"%","rank":51,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-5-9b","modelName":"Qwen3.5-9B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5-9B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 9B","score":82.5,"unit":"%","rank":53,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"minimax-m2","modelName":"MiniMax-M2","provider":"MiniMax","rawName":"MiniMax-M2","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 229B","score":82,"unit":"%","rank":54,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-4-1","modelName":"GPT-4.1","provider":"OpenAI","rawName":"GPT-4.1","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":81.8,"unit":"%","rank":55,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"glm-4-5-air","modelName":"GLM-4.5-Air","provider":"Zhipu AI (Z.ai)","rawName":"GLM-4.5-Air","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 106B","score":81.4,"unit":"%","rank":56,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-v3-mar-2025","modelName":"DeepSeek-V3 (Mar 2025)","provider":"DeepSeek","rawName":"Deepseek-V3-0324","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 671B","score":81.3,"unit":"%","rank":57,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"minimax-m1","modelName":"MiniMax-M1","provider":"MiniMax","rawName":"MiniMax-M1","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 456B","score":81.1,"unit":"%","rank":58,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"kimi-k2-jul-2025","modelName":"Kimi K2 (Jul 2025)","provider":"Moonshot AI","rawName":"Kimi-K2-Instruct","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 1000B","score":81,"unit":"%","rank":59,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-30b-a3b-thinking-jul-2025","modelName":"Qwen3-30B-A3B-Thinking (Jul 2025)","provider":"Alibaba (Qwen)","rawName":"Qwen3-30B-A3B-Thinking-2507","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 30B","score":80.9,"unit":"%","rank":60,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-oss-120b","modelName":"gpt-oss-120b","provider":"OpenAI","rawName":"GPT-oss-120B(high)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 120B","score":80.8,"unit":"%","rank":61,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama4-maverick","modelName":"Llama4-Maverick","provider":"Meta","rawName":"Llama4-Maverick","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 400B","score":80.5,"unit":"%","rank":62,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-o1-mini","modelName":"GPT-o1-mini","provider":"OpenAI","rawName":"GPT-o1-mini","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":80.3,"unit":"%","rank":63,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"doubao-1-5-pro","modelName":"Doubao-1.5-Pro","provider":"ByteDance","rawName":"Doubao-1.5-Pro","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":80.1,"unit":"%","rank":64,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"minimax-m2-5","modelName":"MiniMax-M2.5","provider":"MiniMax","rawName":"MiniMax-M2.5","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 229B","score":80.1,"unit":"%","rank":64,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"grok3-beta","modelName":"Grok3-Beta","provider":"xAI","rawName":"Grok3-Beta","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":79.9,"unit":"%","rank":66,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-o3-mini","modelName":"GPT-o3-mini","provider":"OpenAI","rawName":"GPT-o3-mini","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":79.4,"unit":"%","rank":67,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-2-0-pro","modelName":"Gemini 2.0 Pro","provider":"Google","rawName":"Gemini-2.0-Pro","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":79.1,"unit":"%","rank":68,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-5-4b","modelName":"Qwen3.5-4B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5-4B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 4B","score":79.1,"unit":"%","rank":68,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"hunyuanturbos","modelName":"HunyuanTurboS","provider":"Tencent","rawName":"HunyuanTurboS","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 560B","score":79,"unit":"%","rank":70,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"grok3-mini-beta","modelName":"Grok3-mini-Beta","provider":"xAI","rawName":"Grok3-mini-Beta","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":78.9,"unit":"%","rank":71,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-30b-a3b","modelName":"Qwen3-30B-A3B","provider":"Alibaba (Qwen)","rawName":"Qwen3-30B-A3B-Thinking","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 30B","score":78.5,"unit":"%","rank":72,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"ernie-4-5-300b-a47b","modelName":"ERNIE-4.5-300B-A47B","provider":"Baidu","rawName":"ERNIE-4.5-300B-A47B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 300B","score":78.4,"unit":"%","rank":73,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"nemotron-3-nano-30b-a3b-bf16","modelName":"Nemotron-3-Nano-30B-A3B(BF16)","provider":"NVIDIA","rawName":"Nemotron-3-Nano-30B-A3B(BF16)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 30B","score":78.3,"unit":"%","rank":74,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"nemotron-3-nano-30b-a3b-fp8","modelName":"Nemotron-3-Nano-30B-A3B(FP8)","provider":"NVIDIA","rawName":"Nemotron-3-Nano-30B-A3B(FP8)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 30B","score":78.1,"unit":"%","rank":75,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-3-5-sonnet","modelName":"Claude 3.5 Sonnet","provider":"Anthropic","rawName":"Claude-3.5-Sonnet (2024-10-22)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":78,"unit":"%","rank":76,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-4o-may-2024","modelName":"GPT-4o (May 2024)","provider":"OpenAI","rawName":"GPT-4o (2024-11-20)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":77.9,"unit":"%","rank":77,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-3-5-sonnet","modelName":"Claude 3.5 Sonnet","provider":"Anthropic","rawName":"Claude-3.5-Sonnet (2024-10-22)","variant":"overall","setting":"Overall accuracy; data source: TIGER-LAb","score":77.64,"unit":"%","rank":78,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-2-0-flash","modelName":"gemini-2.0-flash","provider":"Google","rawName":"Gemini-2.0-Flash","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":77.6,"unit":"%","rank":79,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-2-0-flash-dec-2024","modelName":"Gemini 2.0 Flash (Dec 2024)","provider":"Google","rawName":"Gemini-2.0-Flash-exp","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":76.24,"unit":"%","rank":80,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-3-5-sonnet","modelName":"Claude 3.5 Sonnet","provider":"Anthropic","rawName":"Claude-3.5-Sonnet (2024-06-20)","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":76.12,"unit":"%","rank":81,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-5-max","modelName":"Qwen2.5-Max","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-Max","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":76.1,"unit":"%","rank":82,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"phi-4-reasoning-plus","modelName":"Phi-4-reasoning-plus","provider":"Microsoft","rawName":"Phi-4-reasoning-plus","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 14B","score":76,"unit":"%","rank":83,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-v3","modelName":"DeepSeek-V3","provider":"DeepSeek","rawName":"Deepseek-V3","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 671B","score":75.87,"unit":"%","rank":84,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"minimax-text-01","modelName":"MiniMax-Text-01","provider":"MiniMax","rawName":"MiniMax-Text-01","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 456B","score":75.7,"unit":"%","rank":85,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"grok-2","modelName":"Grok-2","provider":"xAI","rawName":"Grok-2","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":75.46,"unit":"%","rank":86,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"grok-4-1-fast-non-reasoning","modelName":"Grok-4.1-Fast(Non-Reasoning)","provider":"xAI","rawName":"Grok-4.1-Fast(Non-Reasoning)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":75.2,"unit":"%","rank":87,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama4-scout","modelName":"Llama4-Scout","provider":"Meta","rawName":"Llama4-Scout","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 109B","score":74.3,"unit":"%","rank":88,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-oss-20b","modelName":"gpt-oss-20b","provider":"OpenAI","rawName":"GPT-oss-20B(high)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 20B","score":73.6,"unit":"%","rank":89,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-3-1-405b","modelName":"Llama 3.1-405B","provider":"Meta","rawName":"Llama-3.1-405B-Instruct","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 405B","score":73.3,"unit":"%","rank":90,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-oss-20b","modelName":"gpt-oss-20b","provider":"OpenAI","rawName":"GPT-oss-20B(medium)","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 20B","score":73.14,"unit":"%","rank":91,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"athene-v2-chat-0-shot","modelName":"Athene-V2-Chat (0-shot)","provider":"Nexusflow","rawName":"Athene-V2-Chat (0-shot)","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 72B","score":73.11,"unit":"%","rank":92,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-4o-may-2024","modelName":"GPT-4o (May 2024)","provider":"OpenAI","rawName":"GPT-4o (2024-05-13)","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":72.55,"unit":"%","rank":93,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"grok-2-mini","modelName":"Grok-2-mini","provider":"xAI","rawName":"Grok-2-mini","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":71.85,"unit":"%","rank":94,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-2-0-flash-lite","modelName":"Gemini-2.0-Flash-Lite","provider":"Google","rawName":"Gemini-2.0-Flash-Lite","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":71.6,"unit":"%","rank":95,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-5-72b","modelName":"Qwen2.5-72B","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-72B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 72B","score":71.59,"unit":"%","rank":96,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"echo-ego-v2-14b","modelName":"ECHO_Ego_v2_14B","provider":null,"rawName":"ECHO_Ego_v2_14B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 14B","score":71.24,"unit":"%","rank":97,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwq-32b-preview","modelName":"QwQ-32B-Preview","provider":"Alibaba (Qwen)","rawName":"QwQ-32B-Preview","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 32B","score":70.97,"unit":"%","rank":98,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"phi-4","modelName":"Phi-4","provider":"Microsoft Research","rawName":"Phi-4","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 14B","score":70.4,"unit":"%","rank":99,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-1-5-pro-sept-2024","modelName":"Gemini 1.5 Pro (Sept 2024)","provider":"Google","rawName":"Gemini-1.5-Pro-002","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":70.25,"unit":"%","rank":100,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"athene-v2-chat","modelName":"Athene-V2-Chat","provider":"Nexusflow","rawName":"Athene-V2-Chat","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 72B","score":70.21,"unit":"%","rank":101,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"ernie-4-5-300b-a47b-base","modelName":"ERNIE-4.5-300B-A47B-Base","provider":"Baidu","rawName":"ERNIE-4.5-300B-A47B-Base","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 300B","score":69.5,"unit":"%","rank":102,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-5-32b","modelName":"Qwen2.5-32B","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-32B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 32B","score":69.23,"unit":"%","rank":103,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"skythought-t1","modelName":"SkyThought-T1","provider":null,"rawName":"SkyThought-T1","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 32B","score":69.2,"unit":"%","rank":104,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwq-32b","modelName":"QwQ-32B","provider":"Alibaba (Qwen)","rawName":"QwQ-32B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 32B","score":69.07,"unit":"%","rank":105,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-1-5-pro","modelName":"Gemini-1.5-Pro","provider":"Google","rawName":"Gemini-1.5-Pro","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":69.03,"unit":"%","rank":106,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-3-opus","modelName":"Claude 3 Opus","provider":"Anthropic","rawName":"Claude-3-Opus","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":68.45,"unit":"%","rank":107,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-235b-a22b","modelName":"Qwen3-235B-A22B","provider":"Alibaba (Qwen)","rawName":"Qwen3-235B-A22B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 235B","score":68.18,"unit":"%","rank":108,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mistral-large-2-nov-2024","modelName":"Mistral Large 2 (Nov 2024)","provider":"Mistral AI","rawName":"Mistral-Large-Instruct-2411","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 123B","score":67.94,"unit":"%","rank":109,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemma-3-27b","modelName":"Gemma 3 27B","provider":"Google","rawName":"Gemma-3-27B-it","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 27B","score":67.5,"unit":"%","rank":110,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"hunyuan-a13b","modelName":"Hunyuan-A13B","provider":"Tencent","rawName":"Hunyuan-A13B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 80B","score":67.3,"unit":"%","rank":111,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mistral-3-1-small","modelName":"Mistral-3.1-Small","provider":"Mistral AI","rawName":"Mistral-3.1-Small","variant":"overall","setting":"Overall accuracy; data source: Sefl-Reported; 24B","score":66.8,"unit":"%","rank":112,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"general-reasoner-14b","modelName":"General-Reasoner-14B","provider":null,"rawName":"General-Reasoner-14B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 14B","score":66.6,"unit":"%","rank":113,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mistral-small-instruct","modelName":"Mistral-Small-instruct","provider":"Mistral AI","rawName":"Mistral-Small-instruct","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 24B","score":66.3,"unit":"%","rank":114,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-3-3-70b","modelName":"Llama 3.3 70B","provider":"Meta","rawName":"Llama-3.3-70B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 70B","score":65.92,"unit":"%","rank":115,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mistral-large-2-jul-2024","modelName":"Mistral Large 2 (Jul 2024)","provider":"Mistral AI","rawName":"Mistral-Large-Instruct-2407","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 123B","score":65.91,"unit":"%","rank":116,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-chat-v2-5","modelName":"DeepSeek-Chat-V2_5","provider":"DeepSeek","rawName":"DeepSeek-Chat-V2_5","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 236B","score":65.83,"unit":"%","rank":117,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"seed-oss-36b-base-w-syn","modelName":"syn.)","provider":"ByteDance","rawName":"Seed-OSS-36B-Base(w/ syn.)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 36B","score":65.1,"unit":"%","rank":118,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"nemotron-3-nano-30b-a3b-base","modelName":"Nemotron-3-Nano-30B-A3B-Base","provider":"NVIDIA","rawName":"Nemotron-3-Nano-30B-A3B-Base","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 30B","score":65.1,"unit":"%","rank":118,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"reka-3","modelName":"Reka 3","provider":"Reka","rawName":"Reka 3","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 21B","score":65,"unit":"%","rank":120,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-72b-chat","modelName":"Qwen2-72B-Chat","provider":"Alibaba (Qwen)","rawName":"Qwen2-72B-Chat","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 72B","score":64.38,"unit":"%","rank":121,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-1-5-flash-sep-2024","modelName":"Gemini 1.5 Flash (Sep 2024)","provider":"Google","rawName":"Gemini-1.5-Flash-002","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":64.09,"unit":"%","rank":122,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"magnum-72b-v1","modelName":"magnum-72b-v1","provider":null,"rawName":"magnum-72b-v1","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 72B","score":63.93,"unit":"%","rank":123,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-4-turbo-nov-2023","modelName":"GPT-4 Turbo (Nov 2023)","provider":"OpenAI","rawName":"GPT-4-Turbo","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":63.71,"unit":"%","rank":124,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-5-14b","modelName":"Qwen2.5-14B","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-14B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 14B","score":63.69,"unit":"%","rank":125,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-coder-v2-236b","modelName":"DeepSeek-Coder-V2 236B","provider":"DeepSeek","rawName":"DeepSeek-Coder-V2-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 236B","score":63.63,"unit":"%","rank":126,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"higgs-llama-3-70b","modelName":"Higgs-Llama-3-70B","provider":null,"rawName":"Higgs-Llama-3-70B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 70B","score":63.16,"unit":"%","rank":127,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gpt-4o-mini","modelName":"GPT-4o mini","provider":"OpenAI","rawName":"GPT-4o-mini","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":63.09,"unit":"%","rank":128,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"azerogpt","modelName":"azerogpt","provider":null,"rawName":"azerogpt","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":63.07,"unit":"%","rank":129,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-3-1-nemotron-70b-instruct-hf","modelName":"Llama-3.1-Nemotron-70B-Instruct-HF","provider":"NVIDIA","rawName":"Llama-3.1-Nemotron-70B-Instruct-HF","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 70B","score":62.78,"unit":"%","rank":130,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"yi-lightning","modelName":"Yi-Lightning","provider":"01.AI","rawName":"Yi-Lightning","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":62.38,"unit":"%","rank":131,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-3-5-haiku","modelName":"Claude 3.5 Haiku","provider":"Anthropic","rawName":"Claude-3-5-Haiku-20241022","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":62.12,"unit":"%","rank":132,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"rrd2-5-9b","modelName":"RRD2.5-9B","provider":null,"rawName":"RRD2.5-9B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 9B","score":61.84,"unit":"%","rank":133,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-30b-a3b-base","modelName":"Qwen3-30B-A3B-Base","provider":"Alibaba (Qwen)","rawName":"Qwen3-30B-A3B-Base","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 30B","score":61.7,"unit":"%","rank":134,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemma-3-12b","modelName":"Gemma 3 12B","provider":"Google","rawName":"Gemma-3-12B-it","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 12B","score":60.6,"unit":"%","rank":135,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"nemotron-h-56b-base","modelName":"Nemotron-H-56B-Base","provider":"NVIDIA","rawName":"Nemotron-H-56B-Base","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 56B","score":60.5,"unit":"%","rank":136,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"seed-oss-36b-base-w-o-syn","modelName":"o syn.)","provider":"ByteDance","rawName":"Seed-OSS-36B-Base(w/o syn.)","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 36B","score":60.4,"unit":"%","rank":137,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"reflection-llama-3-1-70b","modelName":"Reflection-Llama-3.1-70B","provider":null,"rawName":"Reflection-Llama-3.1-70B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 70B","score":60.35,"unit":"%","rank":138,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"hunyuan-large","modelName":"Hunyuan-Large","provider":"Tencent","rawName":"Hunyuan-Large","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 389B","score":60.2,"unit":"%","rank":139,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemini-1-5-flash","modelName":"Gemini-1.5-Flash","provider":"Google","rawName":"Gemini-1.5-Flash","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":59.12,"unit":"%","rank":140,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"exaone-3-5-32b-instruct","modelName":"EXAONE-3.5-32B-Instruct","provider":"LGAI-EXAONE","rawName":"EXAONE-3.5-32B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 32B","score":58.91,"unit":"%","rank":141,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"general-reasoner-7b","modelName":"General-Reasoner-7B","provider":null,"rawName":"General-Reasoner-7B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 7B","score":58.9,"unit":"%","rank":142,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mimo-7b-rl","modelName":"Mimo-7B-RL","provider":"Xiaomi","rawName":"Mimo-7B-RL","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 7B","score":58.6,"unit":"%","rank":143,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"yi-large","modelName":"Yi-Large","provider":"01.AI","rawName":"Yi-large","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 150B","score":58.09,"unit":"%","rank":144,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"phi4-sft","modelName":"Phi4-sft","provider":null,"rawName":"NewenAI/Phi4-sft","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 14B","score":57.7,"unit":"%","rank":145,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"internlm3-8b-instruct","modelName":"Internlm3-8B-Instruct","provider":"Shanghai AI Lab (InternLM)","rawName":"Internlm3-8B-Instruct","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 8B","score":57.6,"unit":"%","rank":146,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-3-sonnet","modelName":"Claude 3 Sonnet","provider":"Anthropic","rawName":"Claude-3-Sonnet","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":56.8,"unit":"%","rank":147,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"ernie-4-5-21b-a3b-base","modelName":"ERNIE-4.5-21B-A3B-Base","provider":"Baidu","rawName":"ERNIE-4.5-21B-A3B-Base","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 21B","score":56.7,"unit":"%","rank":148,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemma-2-27b","modelName":"Gemma 2 27B","provider":"Google","rawName":"Gemma-2-27B-it","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 27B","score":56.54,"unit":"%","rank":149,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mixtral-8x22b","modelName":"Mixtral 8x22B","provider":"Mistral AI","rawName":"Mixtral-8x22B-Instruct-v0.1","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 176B","score":56.33,"unit":"%","rank":150,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-3-70b-instruct","modelName":"Llama-3-70B-Instruct","provider":"Meta","rawName":"Llama-3-70B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 70B","score":56.2,"unit":"%","rank":151,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-5-turbo","modelName":"Qwen2.5-Turbo","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-Turbo","variant":"overall","setting":"Overall accuracy; data source: Self-Reported","score":55.6,"unit":"%","rank":152,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-72b","modelName":"Qwen2-72B","provider":"Alibaba (Qwen)","rawName":"Qwen2-72B-32k","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 72B","score":55.59,"unit":"%","rank":153,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-5-2b","modelName":"Qwen3.5-2B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5-2B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 2B","score":55.3,"unit":"%","rank":154,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-v2-chat","modelName":"Deepseek-V2-Chat","provider":"DeepSeek","rawName":"Deepseek-V2-Chat","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 236B","score":54.81,"unit":"%","rank":155,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mistral-small-base","modelName":"Mistral-Small-base","provider":"Mistral AI","rawName":"Mistral-Small-base","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 24B","score":54.4,"unit":"%","rank":156,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"phi-4-mini","modelName":"Phi-4-mini","provider":"Microsoft","rawName":"Phi-4-mini","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 5.6B","score":52.8,"unit":"%","rank":157,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-3-70b","modelName":"Llama 3-70B","provider":"Meta","rawName":"Llama-3-70B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 70B","score":52.78,"unit":"%","rank":158,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen1-5-72b","modelName":"Qwen1.5-72B","provider":"Alibaba (Qwen)","rawName":"Qwen1.5-72B-Chat","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 72B","score":52.64,"unit":"%","rank":159,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-3-1-70b","modelName":"Llama 3.1-70B","provider":"Meta","rawName":"Llama-3.1-70B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 70B","score":52.47,"unit":"%","rank":160,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"yi-1-5-34b","modelName":"Yi-1.5-34B","provider":"01.AI","rawName":"Yi-1.5-34B-Chat","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 34B","score":52.29,"unit":"%","rank":161,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"phi3","modelName":"Phi3-medium-128k","provider":null,"rawName":"Phi3-medium-128k","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 14B","score":51.91,"unit":"%","rank":162,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mammoth2-8x7b-plus","modelName":"MAmmoTH2-8x7B-Plus","provider":null,"rawName":"MAmmoTH2-8x7B-Plus","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 56B","score":50.4,"unit":"%","rank":163,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen1-5-110b","modelName":"Qwen1.5-110B","provider":"Alibaba (Qwen)","rawName":"Qwen1.5-110B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 110B","score":49.93,"unit":"%","rank":164,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"jamba-1-5-large","modelName":"Jamba 1.5 Large","provider":"AI21 Labs","rawName":"Jamba-1.5-Large","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 399B","score":49.46,"unit":"%","rank":165,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mistral-small-instruct-2409","modelName":"Mistral-Small-Instruct-2409","provider":"Mistral AI","rawName":"Mistral-Small-Instruct-2409","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 22B","score":48.4,"unit":"%","rank":166,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"glm-4-9b-chat","modelName":"GLM-4-9B-Chat","provider":"Zhipu AI (Z.ai)","rawName":"GLM-4-9B-Chat","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 9B","score":48.01,"unit":"%","rank":167,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"glm-4-9b","modelName":"GLM-4-9B","provider":"Zhipu AI (Z.ai)","rawName":"GLM-4-9B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 9B","score":47.92,"unit":"%","rank":168,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"phi-3-5-mini","modelName":"Phi-3.5-mini","provider":"Microsoft","rawName":"Phi-3.5-mini-instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 3.8B","score":47.87,"unit":"%","rank":169,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-7b","modelName":"Qwen2-7B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen2-7B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":47.24,"unit":"%","rank":170,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"cohere-aya-vision","modelName":"Cohere-Aya-Vision","provider":null,"rawName":"Cohere-Aya-Vision","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 32B","score":47.2,"unit":"%","rank":171,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"exaone-3-5-7-8b-instruct","modelName":"EXAONE-3.5-7.8B-Instruct","provider":"LGAI-EXAONE","rawName":"EXAONE-3.5-7.8B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7.8B","score":46.24,"unit":"%","rank":172,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"yi-1-5-9b-chat","modelName":"Yi-1.5-9B-Chat","provider":"01.AI","rawName":"Yi-1.5-9B-Chat","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 9B","score":45.95,"unit":"%","rank":173,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"aya-expanse-32b","modelName":"Aya-Expanse-32B","provider":"Cohere","rawName":"Aya-Expanse-32B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 32B","score":45.41,"unit":"%","rank":174,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemma-2-9b","modelName":"Gemma 2 9B","provider":"Google","rawName":"Gemma-2-9B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 9B","score":45.1,"unit":"%","rank":175,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-5-7b","modelName":"Qwen2.5-7B","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-7B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 7B","score":45,"unit":"%","rank":176,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mistral-nemo","modelName":"Mistral NeMo","provider":"Mistral AI","rawName":"Mistral-Nemo-Instruct-2407","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 12B","score":44.81,"unit":"%","rank":177,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"nemotron-h-8b-base","modelName":"Nemotron-H-8B-Base","provider":"NVIDIA","rawName":"Nemotron-H-8B-Base","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 8B","score":44,"unit":"%","rank":178,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"phi3-mini","modelName":"Phi3-mini-128k","provider":null,"rawName":"Phi3-mini-128k","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 3.8B","score":43.86,"unit":"%","rank":179,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-5-3b","modelName":"Qwen2.5-3B","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-3B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 3B","score":43.73,"unit":"%","rank":180,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemma-3-4b","modelName":"Gemma 3 4B","provider":"Google","rawName":"Gemma-3-4B-it","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 4B","score":43.6,"unit":"%","rank":181,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mammoth2-8b-plus","modelName":"MAmmoTH2-8B-Plus","provider":null,"rawName":"MAmmoTH2-8B-Plus","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 8B","score":43.35,"unit":"%","rank":182,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mixtral-8x7b","modelName":"Mixtral 8x7B","provider":"Mistral AI","rawName":"Mixtral-8x7B-Instruct-v0.1","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 56B","score":43.27,"unit":"%","rank":183,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"yi-34b","modelName":"Yi-34B","provider":"01.AI","rawName":"Yi-34B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 34B","score":43.03,"unit":"%","rank":184,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"claude-3-haiku","modelName":"Claude 3 Haiku","provider":"Anthropic","rawName":"Claude-3-Haiku-20240307","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab","score":42.29,"unit":"%","rank":185,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mathstral-7b-v0-1","modelName":"Mathstral-7B-v0.1","provider":null,"rawName":"Mathstral-7B-v0.1","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":42,"unit":"%","rank":186,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mimo-7b-base","modelName":"Mimo-7B-base","provider":"Xiaomi","rawName":"Mimo-7B-base","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 7B","score":41.9,"unit":"%","rank":187,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-coder-v2-lite-instruct","modelName":"DeepSeek-Coder-V2-Lite-Instruct","provider":"DeepSeek","rawName":"DeepSeek-Coder-V2-Lite-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 16B","score":41.57,"unit":"%","rank":188,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"granite-3-1-8b-instruct","modelName":"Granite-3.1-8B-Instruct","provider":"IBM","rawName":"Granite-3.1-8B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 8B","score":41.03,"unit":"%","rank":189,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-3-8b-instruct","modelName":"Llama-3-8B-Instruct","provider":"Meta","rawName":"Llama-3-8B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 8B","score":40.98,"unit":"%","rank":190,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mammoth2-7b-plus","modelName":"MAmmoTH2-7B-Plus","provider":null,"rawName":"MAmmoTH2-7B-Plus","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":40.85,"unit":"%","rank":191,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"wizardlm-2-8x22b","modelName":"WizardLM-2 8x22B","provider":"Microsoft","rawName":"WizardLM-2-8x22B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 176B","score":39.24,"unit":"%","rank":192,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"exaone-3-5-2-4b-instruct","modelName":"EXAONE-3.5-2.4B-Instruct","provider":"LGAI-EXAONE","rawName":"EXAONE-3.5-2.4B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 2.4B","score":39.1,"unit":"%","rank":193,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"yi-1-5-6b-chat","modelName":"Yi-1.5-6B-Chat","provider":"01.AI","rawName":"Yi-1.5-6B-Chat","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 6B","score":38.23,"unit":"%","rank":194,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen1-5-14b","modelName":"Qwen1.5-14B","provider":"Alibaba (Qwen)","rawName":"Qwen1.5-14B-Chat","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 14B","score":38.02,"unit":"%","rank":195,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"ministral-8b","modelName":"Ministral 8B","provider":"Mistral AI","rawName":"Ministral-8B-Instruct-2410","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 8B","score":37.93,"unit":"%","rank":196,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"c4ai-command-r-v01","modelName":"c4ai-command-r-v01","provider":"Cohere","rawName":"c4ai-command-r-v01","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 35B","score":37.9,"unit":"%","rank":197,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"staring-7b","modelName":"Staring-7B","provider":null,"rawName":"Staring-7B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":37.9,"unit":"%","rank":197,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-2-70b","modelName":"Llama 2-70B","provider":"Meta","rawName":"Llama-2-70B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 70B","score":37.53,"unit":"%","rank":199,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"openchat-3-5-8b","modelName":"OpenChat-3.5-8B","provider":null,"rawName":"OpenChat-3.5-8B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 8B","score":37.24,"unit":"%","rank":200,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"internmath-20b-plus","modelName":"InternMath-20B-Plus","provider":null,"rawName":"InternMath-20B-Plus","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 20B","score":37.1,"unit":"%","rank":201,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llada","modelName":"LLaDA","provider":null,"rawName":"LLaDA","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 8B","score":37,"unit":"%","rank":202,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama3-smaug-8b","modelName":"Llama3-Smaug-8B","provider":"Meta","rawName":"Llama3-Smaug-8B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 8B","score":36.93,"unit":"%","rank":203,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-3-1-8b","modelName":"Llama 3.1-8B","provider":"Meta","rawName":"Llama-3.1-8B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 8B","score":36.6,"unit":"%","rank":204,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-3-8b","modelName":"Llama 3-8B","provider":"Meta","rawName":"Llama-3-8B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 8B","score":35.36,"unit":"%","rank":205,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseekmath-7b-instruct","modelName":"DeepseekMath-7B-Instruct","provider":"DeepSeek","rawName":"DeepseekMath-7B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":35.3,"unit":"%","rank":206,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"deepseek-coder-v2-lite-base","modelName":"DeepSeek-Coder-V2-Lite-Base","provider":"DeepSeek","rawName":"DeepSeek-Coder-V2-Lite-Base","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 16B","score":34.37,"unit":"%","rank":207,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"aya-expanse-8b","modelName":"Aya-Expanse-8B","provider":"Cohere","rawName":"Aya-Expanse-8B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 8B","score":33.74,"unit":"%","rank":208,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemma-7b","modelName":"Gemma 7B","provider":"Google","rawName":"Gemma-7B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":33.73,"unit":"%","rank":209,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"internmath-7b-plus","modelName":"InternMath-7B-Plus","provider":null,"rawName":"InternMath-7B-Plus","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":33.5,"unit":"%","rank":210,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"granite-3-1-8b-base","modelName":"Granite-3.1-8B-Base","provider":"IBM","rawName":"Granite-3.1-8B-Base","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 8B","score":33.08,"unit":"%","rank":211,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"zephyr-7b-beta","modelName":"Zephyr-7B-Beta","provider":"Hugging Face","rawName":"Zephyr-7B-Beta","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":32.97,"unit":"%","rank":212,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-5-1-5b","modelName":"Qwen2.5-1.5B","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-1.5B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 1.5B","score":32.1,"unit":"%","rank":213,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"granite-3-1-2b-instruct","modelName":"Granite-3.1-2B-Instruct","provider":"IBM","rawName":"Granite-3.1-2B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 2B","score":31.97,"unit":"%","rank":214,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"granite-3-0-8b-base","modelName":"Granite-3.0-8B-Base","provider":"IBM","rawName":"Granite-3.0-8B-Base","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 8B","score":31.03,"unit":"%","rank":215,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mistral-7b-v0-1","modelName":"Mistral 7B v0.1","provider":"Mistral AI","rawName":"Mistral-7B-v0.1","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":30.88,"unit":"%","rank":216,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"mistral-7b-v0-2","modelName":"Mistral 7B v0.2","provider":"Mistral AI","rawName":"Mistral-7B-Instruct-v0.2","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":30.84,"unit":"%","rank":217,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen3-5-0-8b","modelName":"Qwen3.5-0.8B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5-0.8B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 0.8B","score":29.7,"unit":"%","rank":218,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen1-5-7b","modelName":"Qwen1.5-7B","provider":"Alibaba (Qwen)","rawName":"Qwen1.5-7B-Chat","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":29.06,"unit":"%","rank":219,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"yi-6b","modelName":"Yi 6B","provider":"01.AI","rawName":"Yi-6B-Chat","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 6B","score":28.84,"unit":"%","rank":220,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"neo-7b-instruct","modelName":"Neo-7B-Instruct","provider":null,"rawName":"Neo-7B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":28.74,"unit":"%","rank":221,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"neo-7b","modelName":"Neo-7B","provider":null,"rawName":"Neo-7B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":25.85,"unit":"%","rank":222,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"granite-3-1-3b-a800m-instruct","modelName":"Granite-3.1-3B-A800M-Instruct","provider":"IBM","rawName":"Granite-3.1-3B-A800M-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 3B","score":25.42,"unit":"%","rank":223,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-2-13b","modelName":"Llama 2-13B","provider":"Meta","rawName":"Llama-2-13B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 13B","score":25.34,"unit":"%","rank":224,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"granite-3-1-2b-base","modelName":"Granite-3.1-2B-Base","provider":"IBM","rawName":"Granite-3.1-2B-Base","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 2B","score":23.89,"unit":"%","rank":225,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llemma-7b","modelName":"Llemma-7B","provider":null,"rawName":"Llemma-7B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":23.45,"unit":"%","rank":226,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-1-5b-instruct","modelName":"Qwen2-1.5B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen2-1.5B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 1.5B","score":22.62,"unit":"%","rank":227,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-1-5b","modelName":"Qwen2-1.5B","provider":"Alibaba (Qwen)","rawName":"Qwen2-1.5B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 1.5B","score":22.56,"unit":"%","rank":228,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-3-2-3b","modelName":"Llama-3.2-3B-Instruct","provider":"Meta","rawName":"Llama-3.2-3B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 3B","score":22.17,"unit":"%","rank":229,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"granite-3-0-2b-base","modelName":"Granite-3.0-2B-Base","provider":"IBM","rawName":"Granite-3.0-2B-Base","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 2B","score":21.72,"unit":"%","rank":230,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"granite-3-1-3b-a800m-base","modelName":"Granite-3.1-3B-A800M-Base","provider":"IBM","rawName":"Granite-3.1-3B-A800M-Base","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 3B","score":20.39,"unit":"%","rank":231,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-2-7b","modelName":"Llama 2-7B","provider":"Meta","rawName":"Llama-2-7B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 7B","score":20.32,"unit":"%","rank":232,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"smollm2-1-7b","modelName":"SmolLM2-1.7B","provider":"Hugging Face","rawName":"SmolLM2-1.7B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 1.7B","score":18.31,"unit":"%","rank":233,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-0-5b-instruct","modelName":"Qwen2-0.5B-Instruct","provider":"Alibaba (Qwen)","rawName":"Qwen2-0.5B-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 0.5B","score":15.93,"unit":"%","rank":234,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemma-2b","modelName":"Gemma 2B","provider":"Google","rawName":"Gemma-2B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 2B","score":15.85,"unit":"%","rank":235,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemma-2-2b-it","modelName":"Gemma-2-2B-it","provider":"Google","rawName":"Gemma-2-2B-it","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 2B","score":15.6,"unit":"%","rank":236,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-0-5b","modelName":"Qwen2-0.5B","provider":"Alibaba (Qwen)","rawName":"Qwen2-0.5B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 0.5B","score":14.97,"unit":"%","rank":237,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"qwen2-5-0-5b","modelName":"Qwen2.5-0.5B","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-0.5B","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 0.5B","score":14.92,"unit":"%","rank":238,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"gemma-3-1b","modelName":"Gemma 3 1B","provider":"Google","rawName":"Gemma-3-1B-it","variant":"overall","setting":"Overall accuracy; data source: Self-Reported; 1B","score":14.7,"unit":"%","rank":239,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"vendor","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"granite-3-1-1b-a400m-instruct","modelName":"Granite-3.1-1B-A400M-Instruct","provider":"IBM","rawName":"Granite-3.1-1B-A400M-Instruct","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 1B","score":13.27,"unit":"%","rank":240,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"granite-3-1-1b-a400m-base","modelName":"Granite-3.1-1B-A400M-Base","provider":"IBM","rawName":"Granite-3.1-1B-A400M-Base","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 1B","score":12.34,"unit":"%","rank":241,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"llama-3-2-1b","modelName":"Llama 3.2 1B","provider":"Meta","rawName":"Llama-3.2-1B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 1B","score":11.95,"unit":"%","rank":242,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"smollm-1-7b","modelName":"SmolLM-1.7B","provider":"Hugging Face","rawName":"SmolLM-1.7B","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 1.7B","score":11.93,"unit":"%","rank":243,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"smollm2-360m","modelName":"SmolLM2-360M","provider":"Hugging Face","rawName":"SmolLM2-360M","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 0.36B","score":11.38,"unit":"%","rank":244,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"smollm-135m","modelName":"SmolLM-135M","provider":"Hugging Face","rawName":"SmolLM-135M","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 0.135B","score":11.22,"unit":"%","rank":245,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"smollm-360m","modelName":"SmolLM-360M","provider":"Hugging Face","rawName":"SmolLM-360M","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 0.36B","score":10.95,"unit":"%","rank":246,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"},{"model":"smollm2-135m","modelName":"SmolLM2-135M","provider":"Hugging Face","rawName":"SmolLM2-135M","variant":"overall","setting":"Overall accuracy; data source: TIGER-Lab; 0.135B","score":10.85,"unit":"%","rank":247,"rankComputedBySite":true,"date":"2026-03-11","sourceType":"official","source":"mmlupro","sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","collected":"2026-10-10"}]}