MMLU Pro
Academic multiple-choice benchmark covering 14 subjects including STEM, humanities, and social sciences.
107rows
scoreprimary metric
2026-05-28sampled
Metadata
Metrics
Score, Std. error (lower is better), Latency (lower is better), Cost per test (lower is better)
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Gemini 3.1 Pro Preview | 90.987% | Gemini 3.1 Pro Preview google-gemini-3.1-pro-preview | Imported | 2026-05-28 |
| 2 | Gemini 3 Pro Preview | 90.102% | Gemini 3 google-gemini-3 | Imported | 2026-05-28 |
| 3 | Claude Opus 4.7 | 89.871% | Claude Opus 4.7 anthropic-claude-opus-4.7 | Imported | 2026-05-28 |
| 4 | Claude Opus 4.8 | 89.585% | Claude Opus 4.8 anthropic-claude-opus-4.8 | Imported | 2026-05-28 |
| 5 | Gemini 3.5 Flash | 89.515% | Gemini 3.5 Flash google-gemini-3.5-flash | Imported | 2026-05-28 |
| 6 | Qwen 3.7 Max | 89.311% | Qwen3.7 Max qwen-qwen3.7-max | Imported | 2026-05-28 |
| 7 | Claude Opus 4.6 Thinking | 89.107% | Claude Opus 4.6 anthropic-claude-opus-4.6 | Imported | 2026-05-28 |
| 8 | Gemini 3 Flash Preview | 88.592% | Gemini 3 Flash Preview google-gemini-3-flash-preview | Imported | 2026-05-28 |
| 9 | GPT 5.5 | 88.144% | GPT-5.5 openai-gpt-5.5 | Imported | 2026-05-28 |
| 10 | Claude Opus 4.1 20250805 Thinking | 87.924% | Claude Opus 4.1 anthropic-claude-opus-4.1 | Imported | 2026-05-28 |
| 11 | Qwen 3.6 Plus | 87.668% | Qwen3.6 Plus qwen-qwen3.6-plus | Imported | 2026-05-28 |
| 12 | Kimi K2.6 Thinking | 87.572% | MoonshotAI: Kimi K2.6 moonshotai-kimi-k2.6 | Imported | 2026-05-28 |
| 13 | GPT 5.4 2026-03-05 | 87.482% | GPT-5.4 openai-gpt-5.4 | Imported | 2026-05-28 |
| 14 | Claude Sonnet 4.5 20250929 Thinking | 87.357% | Claude Sonnet 4.5 anthropic-claude-sonnet-4.5 | Imported | 2026-05-28 |
| 15 | Claude Sonnet 4.6 | 87.341% | Claude Sonnet 4.6 anthropic-claude-sonnet-4.6 | Imported | 2026-05-28 |
| 16 | Muse Spark | 87.316% | — | Imported | 2026-05-28 |
| 17 | Claude Opus 4.5 20251101 Thinking | 87.26% | Claude Opus 4.5 anthropic-claude-opus-4.5 | Imported | 2026-05-28 |
| 18 | DeepSeek V4 Pro | 87.249% | DeepSeek V4 Pro deepseek-deepseek-v4-pro | Imported | 2026-05-28 |
| 19 | Claude Opus 4.1 20250805 | 87.214% | Claude Opus 4.1 anthropic-claude-opus-4.1 | Imported | 2026-05-28 |
| 20 | Qwen 3.5 Plus Thinking | 87.178% | — | Imported | 2026-05-28 |
| 21 | MiniMax M2.1 | 87.049% | MiniMax M2.1 minimax-minimax-m2.1 | Imported | 2026-05-28 |
| 22 | GLM 5.1 Thinking | 86.9% | GLM 5.1 z-ai-glm-5.1 | Imported | 2026-05-28 |
| 23 | GPT 5.2025-08-07 | 86.544% | GPT-5 openai-gpt-5 | Imported | 2026-05-28 |
| 24 | GPT 5.1 2025-11-13 | 86.377% | GPT-5.1 openai-gpt-5.1 | Imported | 2026-05-28 |
| 25 | Grok 4.20 0309 Reasoning | 86.254% | Grok 4.20 x-ai-grok-4.20 | Imported | 2026-05-28 |
| 26 | Gemini 3.1 Flash Lite Preview | 86.24% | Gemini 3.1 Flash Lite Preview google-gemini-3.1-flash-lite-preview | Imported | 2026-05-28 |
| 27 | GPT 5.2 2025-12-11 | 86.234% | GPT-5.2 openai-gpt-5.2 | Imported | 2026-05-28 |
| 28 | Claude Opus 4.20250514 | 86.166% | Claude Opus 4 anthropic-claude-opus-4 | Imported | 2026-05-28 |
| 29 | GLM 5 Thinking | 86.03% | GLM 5 z-ai-glm-5 | Imported | 2026-05-28 |
| 30 | Kimi K2.5 Thinking | 85.914% | MoonshotAI: Kimi K2.5 moonshotai-kimi-k2.5 | Imported | 2026-05-28 |
| 31 | Grok 4.3 | 85.838% | Grok 4.3 x-ai-grok-4.3 | Imported | 2026-05-28 |
| 32 | O3 2025-04-16 | 85.595% | o3 openai-o3 | Imported | 2026-05-28 |
| 33 | Claude Opus 4.5 20251101 | 85.59% | Claude Opus 4.5 anthropic-claude-opus-4.5 | Imported | 2026-05-28 |
| 34 | Grok 4.0709 | 85.304% | Grok 4 x-ai-grok-4 | Imported | 2026-05-28 |
| 35 | Qwen 3 Max 2026-01-23 | 84.976% | — | Imported | 2026-05-28 |
| 36 | DeepSeek V3P2 Thinking | 84.917% | — | Imported | 2026-05-28 |
| 37 | GPT 5.4 Mini 2026-03-17 | 84.554% | GPT-5.4 Mini openai-gpt-5.4-mini | Imported | 2026-05-28 |
| 38 | Qwen 3 Max | 84.36% | Qwen3 Max qwen-qwen3-max | Imported | 2026-05-28 |
| 39 | Grok 4.1 Fast Reasoning | 84.18% | Grok 4.1 Fast x-ai-grok-4.1-fast | Imported | 2026-05-28 |
| 40 | Qwen 3.5 Flash | 84.061% | Qwen3.5-Flash qwen-qwen3.5-flash-02-23 | Imported | 2026-05-28 |
| 41 | Gemini 2.5 Pro Exp 03 25 | 84.058% | — | Imported | 2026-05-28 |
| 42 | Claude Sonnet 4.20250514 Thinking | 83.865% | — | Imported | 2026-05-28 |
| 43 | Gemini 2.5 Flash Preview 09 2025 | 83.686% | — | Imported | 2026-05-28 |
| 44 | Gemini 2.5 Flash Preview 09 2025 Thinking | 83.664% | — | Imported | 2026-05-28 |
| 45 | Qwen 3 Max Preview | 83.537% | — | Imported | 2026-05-28 |
| 46 | O1 2024-12-17 | 83.488% | o1 openai-o1 | Imported | 2026-05-28 |
| 47 | DeepSeek R1 | 83.184% | R1 deepseek-r1 | Imported | 2026-05-28 |
| 48 | DeepSeek V3P2 | 83.056% | — | Imported | 2026-05-28 |
| 49 | GLM 4.7 | 82.736% | GLM 4.7 z-ai-glm-4.7 | Imported | 2026-05-28 |
| 50 | Claude 3 7 Sonnet 20250219 Thinking | 82.728% | — | Imported | 2026-05-28 |
| 51 | GPT 5 Mini 2025-08-07 | 82.226% | GPT-5 Mini openai-gpt-5-mini | Imported | 2026-05-28 |
| 52 | GLM 4.6 | 82.203% | GLM 4.6 z-ai-glm-4.6 | Imported | 2026-05-28 |
| 53 | Grok 3 Mini Fast High Reasoning | 81.374% | — | Imported | 2026-05-28 |
| 54 | Qwen 3 235B A22b | 81.246% | Qwen3 235B A22B qwen-qwen3-235b-a22b | Imported | 2026-05-28 |
| 55 | GLM 4.5 | 81.222% | GLM 4.5 z-ai-glm-4.5 | Imported | 2026-05-28 |
| 56 | Kimi K2 Thinking | 81.068% | MoonshotAI: Kimi K2 Thinking moonshotai-kimi-k2-thinking | Imported | 2026-05-28 |
| 57 | Claude 3 7 Sonnet 20250219 | 80.663% | Claude 3.7 Sonnet anthropic-claude-3.7-sonnet | Imported | 2026-05-28 |
| 58 | O4 Mini 2025-04-16 | 80.561% | o4 Mini openai-o4-mini | Imported | 2026-05-28 |
| 59 | GPT 4.1 2025-04-14 | 80.495% | GPT-4.1 openai-gpt-4.1 | Imported | 2026-05-28 |
| 60 | MiniMax M2.7 | 80.427% | MiniMax M2.7 minimax-minimax-m2.7 | Imported | 2026-05-28 |
| 61 | MiniMax M2.5 Lightning | 80.093% | — | Imported | 2026-05-28 |
| 62 | Grok 3 Mini Fast Low Reasoning | 80.011% | — | Imported | 2026-05-28 |
| 63 | Grok 3 | 79.949% | Grok 3 xaigrok-3 | Imported | 2026-05-28 |
| 64 | Mistral Large 2512 | 79.823% | Mistral: Mistral Large 3 2512 mistralai-mistral-large-2512 | Imported | 2026-05-28 |
| 65 | Grok 4 Fast Reasoning | 79.704% | Grok 4 Fast x-ai-grok-4-fast | Imported | 2026-05-28 |
| 66 | DeepSeek V3 0324 | 79.474% | DeepSeek V3 0324 deepseek-deepseek-chat-v3-0324 | Imported | 2026-05-28 |
| 67 | Claude Sonnet 4.20250514 | 79.432% | Claude Sonnet 4 anthropic-claude-sonnet-4 | Imported | 2026-05-28 |
| 68 | Llama4 Maverick Instruct Basic | 79.415% | — | Imported | 2026-05-28 |
| 69 | Kimi K2 Instruct | 79.394% | MoonshotAI: Kimi K2 0711 moonshotai-kimi-k2 | Imported | 2026-05-28 |
| 70 | GPT Oss 120B | 79.166% | gpt-oss-120b openai-gpt-oss-120b | Imported | 2026-05-28 |
| 71 | Gemini 2.5 Flash Lite Preview 09 2025 Thinking | 79.118% | — | Imported | 2026-05-28 |
| 72 | Claude Haiku 4.5 20251001 Thinking | 78.715% | Claude Haiku 4.5 anthropic-claude-haiku-4.5 | Imported | 2026-05-28 |
| 73 | O3 Mini 2025-01-31 | 78.689% | o3-mini openai-o3-mini | Imported | 2026-05-28 |
| 74 | Gemini 2.5 Flash Lite Preview 09 2025 | 78.639% | Gemini 2.5 Flash Lite Preview 09-2025 google-gemini-2.5-flash-lite-preview-09-2025 | Imported | 2026-05-28 |
| 75 | Claude 3 5 Sonnet 20241022 | 78.404% | Claude 3.5 Sonnet anthropic-claude-3.5-sonnet | Imported | 2026-05-28 |
| 76 | Command A Plus 05 2026 | 78.151% | — | Imported | 2026-05-28 |
| 77 | Gemini 2.0 Flash 001 | 77.376% | Gemini 2.0 Flash google-gemini-2.0-flash | Imported | 2026-05-28 |
| 78 | GPT 4.1 Mini 2025-04-14 | 77.225% | GPT-4.1 Mini openai-gpt-4.1-mini | Imported | 2026-05-28 |
| 79 | GPT 5.4 Nano 2026-03-17 | 77.172% | GPT-5.4 Nano openai-gpt-5.4-nano | Imported | 2026-05-28 |
| 80 | GPT 5 Nano 2025-08-07 | 76.067% | GPT-5 Nano openai-gpt-5-nano | Imported | 2026-05-28 |
| 81 | Grok 2.1212 | 75.473% | — | Imported | 2026-05-28 |
| 82 | Mistral Medium 3.5 | 75.335% | Mistral: Mistral Medium 3.5 mistralai-mistral-medium-3-5 | Imported | 2026-05-28 |
| 83 | Gemini 1.5 Pro 002 | 75.294% | — | Imported | 2026-05-28 |
| 84 | Mistral Medium 2505 | 75.29% | — | Imported | 2026-05-28 |
| 85 | Grok 4.1 Fast Non Reasoning | 75.214% | Grok 4.1 Fast x-ai-grok-4.1-fast | Imported | 2026-05-28 |
| 86 | GPT 4O 2024-08-06 | 74.13% | GPT-4o (2024-08-06) openai-gpt-4o-2024-08-06 | Imported | 2026-05-28 |
| 87 | DeepSeek V3 | 73.82% | DeepSeek V3 deepseek-deepseek-chat | Imported | 2026-05-28 |
| 88 | GPT 4O 2024-11-20 | 72.563% | GPT-4o (2024-11-20) openai-gpt-4o-2024-11-20 | Imported | 2026-05-28 |
| 89 | GPT Oss 20B | 71.636% | gpt-oss-20b openai-gpt-oss-20b | Imported | 2026-05-28 |
| 90 | Llama 3.3 Nemotron Super 49B V1 42e84561 | 70.778% | — | Imported | 2026-05-28 |
| 91 | Grok 4 Fast Non Reasoning | 70.342% | Grok 4 Fast x-ai-grok-4-fast | Imported | 2026-05-28 |
| 92 | Llama 3.3 70B Instruct Turbo | 69.86% | — | Imported | 2026-05-28 |
| 93 | Mistral Large 2411 | 69.706% | Mistral Large 2411 mistralai-mistral-large-2411 | Imported | 2026-05-28 |
| 94 | Llama 4 Scout 17B 16E Instruct | 69.632% | Llama 4 Scout meta-llama-llama-4-scout | Imported | 2026-05-28 |
| 95 | Llama 3.3 Nemotron Super 49B V1 42e84561 Thinking | 69.577% | — | Imported | 2026-05-28 |
| 96 | Command A 03 2025 | 69.172% | Command A cohere-command-a | Imported | 2026-05-28 |
| 97 | Magistral Medium 2509 | 68.659% | — | Imported | 2026-05-28 |
| 98 | Mistral Small 2503 | 66.021% | — | Imported | 2026-05-28 |
| 99 | Gemini 1.5 Flash 002 | 65.606% | — | Imported | 2026-05-28 |
| 100 | Mistral Small 2402 | 64.443% | — | Imported | 2026-05-28 |
| 101 | Claude 3 5 Haiku 20241022 | 64.117% | — | Imported | 2026-05-28 |
| 102 | GPT 4.1 Nano 2025-04-14 | 63.479% | GPT-4.1 Nano openai-gpt-4.1-nano | Imported | 2026-05-28 |
| 103 | GPT 4O Mini 2024-07-18 | 62.735% | GPT-4o-mini (2024-07-18) openai-gpt-4o-mini-2024-07-18 | Imported | 2026-05-28 |
| 104 | Magistral Small 2509 | 62.135% | — | Imported | 2026-05-28 |
| 105 | Jamba Large 1.6 | 49.778% | — | Imported | 2026-05-28 |
| 106 | Command R Plus | 44.003% | — | Imported | 2026-05-28 |
| 107 | Jamba Mini 1.6 | 30.278% | — | Imported | 2026-05-28 |
No matching rows.