mmlu-pro is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for mmlu-pro.
Accuracy is the reported evaluation metric for mmlu-pro. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
Muted rows were not state of the art when published — an earlier or same-year result already scored better.
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | Darwin 180B RSI | vendor | 88.12 | N/A | Code ↗ | Looks wrong? |
| 02 | MiniMax M2.1 | vendor | 88 | N/A | Code ↗Source ↗ | Looks wrong? |
| 03 | Intern S2 Preview | vendor | 88 | N/A | Code ↗ | Looks wrong? |
| 04 | Qwen3.5 397B A17B | vendor | 87.8 | N/A | Code ↗ | Looks wrong? |
| 05 | DeepSeek V4 Pro | vendor | 87.5 | N/A | Code ↗ | Looks wrong? |
| 06 | Kimi K2.5 | vendor | 87.1 | N/A | Code ↗ | Looks wrong? |
| 07 | NVIDIA Nemotron 3 Ultra 550B A55B BF16 | vendor | 86.8 | N/A | Code ↗ | Looks wrong? |
| 08 | NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 | vendor | 86.8 | N/A | Code ↗ | Looks wrong? |
| 09 | Qwen3.5 122B A10B | vendor | 86.7 | N/A | Code ↗Source ↗ | Looks wrong? |
| 10 | DeepSeek V4 Flash | vendor | 86.4 | N/A | Code ↗ | Looks wrong? |
| 11 | Qwen3.6 27B | vendor | 86.2 | N/A | Code ↗ | Looks wrong? |
| 12 | Solar Open2 250B | vendor | 86.2 | N/A | Code ↗ | Looks wrong? |
| 13 | Qwen3.5 27B | vendor | 86.1 | N/A | Code ↗Source ↗ | Looks wrong? |
| 14 | GLM 5 | vendor | 86 | N/A | Code ↗Source ↗ | Looks wrong? |
| 15 | Qwen3.6 35B A3B | vendor | 85.2 | N/A | Code ↗ | Looks wrong? |
| 16 | DeepSeek R1 0528 | vendor | 85 | N/A | Code ↗ | Looks wrong? |
| 17 | GLM 4.5 | vendor | 84.6 | N/A | Code ↗Source ↗ | Looks wrong? |
| 18 | Step 3.5 Flash | vendor | 84.4 | N/A | Code ↗Source ↗ | Looks wrong? |
| 19 | DeepSeek R1 | vendor | 84 | N/A | Code ↗ | Looks wrong? |
| 20 | K EXAONE 236B A23B | vendor | 83.8 | N/A | Code ↗ | Looks wrong? |
| 21 | NVIDIA Nemotron 3 Super 120B A12B BF16 | vendor | 83.73 | N/A | Code ↗ | Looks wrong? |
| 22 | Intern S1 | vendor | 83.5 | N/A | Code ↗Source ↗ | Looks wrong? |
| 23 | EXAONE 4.5 33B | vendor | 83.3 | N/A | Code ↗ | Looks wrong? |
| 24 | Qwen3 235B A22B Instruct 2507 | vendor | 83 | N/A | Code ↗Source ↗ | Looks wrong? |
| 25 | Seed OSS 36B Instruct | vendor | 82.7 | N/A | Code ↗Source ↗ | Looks wrong? |
| 26 | LongCat Flash Chat | vendor | 82.7 | N/A | Code ↗Source ↗ | Looks wrong? |
| 27 | MiniMax M2 | vendor | 82 | N/A | Code ↗ | Looks wrong? |
| 28 | NVIDIA Nemotron 3.5 Lightning 30B A3B BF16 | vendor | 81.94 | N/A | Code ↗ | Looks wrong? |
| 29 | NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4 | vendor | 81.62 | N/A | Code ↗ | Looks wrong? |
| 30 | A.X K1 | vendor | 81.5 | N/A | Code ↗ | Looks wrong? |
| 31 | GLM 4.5 Air | vendor | 81.4 | N/A | Code ↗Source ↗ | Looks wrong? |
| 32 | DeepSeek V3 0324 | vendor | 81.2 | N/A | Code ↗ | Looks wrong? |
| 33 | MiniMax M1 40k | vendor | 81.1 | N/A | Code ↗Source ↗ | Looks wrong? |
| 34 | JoyAI LLM Flash | vendor | 81.02 | N/A | Code ↗ | Looks wrong? |
| 35 | Kimi K2 Instruct | vendor | 81 | N/A | Code ↗Source ↗ | Looks wrong? |
| 36 | Qwen3 30B A3B Thinking 2507 | vendor | 80.9 | N/A | Code ↗Source ↗ | Looks wrong? |
| 37 | gpt oss 120b | vendor | 80.8 | N/A | Code ↗Source ↗ | Looks wrong? |
| 38 | MiniMax M2.5 | vendor | 80.1 | N/A | Code ↗Source ↗ | Looks wrong? |
| 39 | ERNIE 4.5 300B A47B PT | vendor | 78.4 | N/A | Code ↗Source ↗ | Looks wrong? |
| 40 | LongCat Flash Lite | vendor | 78.29 | N/A | Code ↗ | Looks wrong? |
| 41 | MiniMax Text 01 | vendor | 75.7 | N/A | Code ↗Source ↗ | Looks wrong? |
| 42 | gpt oss 20b | vendor | 73.6 | N/A | Code ↗Source ↗ | Looks wrong? |
| 43 | GPT-4o | paper | 72.6 | 2024 | Paper ↗ | Looks wrong? |
| 44 | Qwen2.5 72B | vendor | 71.59 | N/A | Code ↗Source ↗ | Looks wrong? |
| 45 | phi 4 | vendor | 70.4 | N/A | Code ↗Source ↗ | Looks wrong? |
| 46 | Qwen3 4B Instruct 2507 | vendor | 69.6 | N/A | Code ↗ | Looks wrong? |
| 47 | ERNIE 4.5 300B A47B Base PT | vendor | 69.5 | N/A | Code ↗Source ↗ | Looks wrong? |
| 48 | Qwen2.5 32B | vendor | 69.23 | N/A | Code ↗Source ↗ | Looks wrong? |
| 49 | Gemini 1.5 Pro | paper | 69 | 2024 | Paper ↗ | Looks wrong? |
| 50 | MiMo V2.5 Pro | vendor | 68.5 | N/A | Code ↗ | Looks wrong? |
| 51 | Claude 3 Opus | paper | 68.5 | 2024 | Paper ↗ | Looks wrong? |
| 52 | Qwen3 235B A22B | vendor | 68.18 | N/A | Code ↗Source ↗ | Looks wrong? |
| 53 | Mistral Large Instruct 2411 | vendor | 67.94 | N/A | Code ↗Source ↗ | Looks wrong? |
| 54 | Hunyuan A13B Instruct | vendor | 67.3 | N/A | Code ↗Source ↗ | Looks wrong? |
| 55 | Mistral Large Instruct 2407 | vendor | 65.91 | N/A | Code ↗Source ↗ | Looks wrong? |
| 56 | DeepSeek V2.5 | vendor | 65.83 | N/A | Code ↗Source ↗ | Looks wrong? |
| 57 | Seed OSS 36B Base | vendor | 65.1 | N/A | Code ↗Source ↗ | Looks wrong? |
| 58 | NVIDIA Nemotron 3 Nano 30B A3B Base BF16 | vendor | 65.1 | N/A | Code ↗Source ↗ | Looks wrong? |
| 59 | DeepSeek V3 | vendor | 64.4 | N/A | Code ↗ | Looks wrong? |
| 60 | granite 4.1 30b | vendor | 64.09 | N/A | Code ↗ | Looks wrong? |
| 61 | GPT-4-Turbo | paper | 63.7 | 2024 | Paper ↗ | Looks wrong? |
| 62 | Qwen2.5 14B | vendor | 63.69 | N/A | Code ↗Source ↗ | Looks wrong? |
| 63 | Qwen3 30B A3B Base | vendor | 61.7 | N/A | Code ↗Source ↗ | Looks wrong? |
| 64 | Llama 3.1 405B | vendor | 61.6 | N/A | Code ↗Source ↗ | Looks wrong? |
| 65 | Nemotron H 56B Base 8K | vendor | 60.5 | N/A | Code ↗Source ↗ | Looks wrong? |
| 66 | Seed OSS 36B Base woSyn | vendor | 60.4 | N/A | Code ↗Source ↗ | Looks wrong? |
| 67 | Tencent Hunyuan Large | vendor | 60.2 | N/A | Code ↗Source ↗ | Looks wrong? |
| 68 | Mellum2 12B A2.5B Base Pretrain | vendor | 59.31 | N/A | Code ↗ | Looks wrong? |
| 69 | Mellum2 12B A2.5B Base | vendor | 59.31 | N/A | Code ↗ | Looks wrong? |
| 70 | Gemini 1.5 Flash | paper | 59.1 | 2024 | Paper ↗ | Looks wrong? |
| 71 | EXAONE 3.5 32B Instruct | vendor | 58.91 | N/A | Code ↗Source ↗ | Looks wrong? |
| 72 | MiMo 7B RL | vendor | 58.6 | N/A | Code ↗Source ↗ | Looks wrong? |
| 73 | internlm3 8b instruct | vendor | 57.6 | N/A | Code ↗Source ↗ | Looks wrong? |
| 74 | ERNIE 4.5 21B A3B Base PT | vendor | 56.7 | N/A | Code ↗Source ↗ | Looks wrong? |
| 75 | Llama 3 70B Instruct | paper | 56.2 | 2024 | Paper ↗ | Looks wrong? |
| 76 | granite 4.1 8b | vendor | 55.99 | N/A | Code ↗ | Looks wrong? |
| 77 | Phi 3 medium 4k instruct | vendor | 55.7 | N/A | Code ↗Source ↗ | Looks wrong? |
| 78 | DeepSeek V2 Chat | vendor | 54.81 | N/A | Code ↗Source ↗ | Looks wrong? |
| 79 | Mistral Small 24B Base 2501 | vendor | 54.4 | N/A | Code ↗Source ↗ | Looks wrong? |
| 80 | Phi 4 mini instruct | vendor | 52.8 | N/A | Code ↗Source ↗ | Looks wrong? |
| 81 | Meta Llama 3 70B | vendor | 52.78 | N/A | Code ↗Source ↗ | Looks wrong? |
| 82 | Llama 3.1 70B | vendor | 52.47 | N/A | Code ↗Source ↗ | Looks wrong? |
| 83 | Yi 1.5 34B Chat | vendor | 52.29 | N/A | Code ↗Source ↗ | Looks wrong? |
| 84 | Phi 3 medium 128k instruct | vendor | 51.91 | N/A | Code ↗Source ↗ | Looks wrong? |
| 85 | MAmmoTH2 8x7B Plus | vendor | 50.4 | N/A | Code ↗Source ↗ | Looks wrong? |
| 86 | Qwen1.5 110B | vendor | 49.93 | N/A | Code ↗Source ↗ | Looks wrong? |
| 87 | granite 4.1 3b | vendor | 49.83 | N/A | Code ↗ | Looks wrong? |
| 88 | AI21 Jamba Large 1.5 | vendor | 49.46 | N/A | Code ↗Source ↗ | Looks wrong? |
| 89 | Mistral Small Instruct 2409 | vendor | 48.4 | N/A | Code ↗Source ↗ | Looks wrong? |
| 90 | glm 4 9b | vendor | 47.92 | N/A | Code ↗Source ↗ | Looks wrong? |
| 91 | Phi 3.5 mini instruct | vendor | 47.87 | N/A | Code ↗Source ↗ | Looks wrong? |
| 92 | EXAONE 3.5 7.8B Instruct | vendor | 46.24 | N/A | Code ↗Source ↗ | Looks wrong? |
| 93 | Yi 1.5 9B Chat | vendor | 45.95 | N/A | Code ↗Source ↗ | Looks wrong? |
| 94 | Phi 3 mini 4k instruct | vendor | 45.66 | N/A | Code ↗Source ↗ | Looks wrong? |
| 95 | aya expanse 32b | vendor | 45.41 | N/A | Code ↗Source ↗ | Looks wrong? |
| 96 | gemma 2 9b | vendor | 45.1 | N/A | Code ↗Source ↗ | Looks wrong? |
| 97 | Qwen2.5 7B | vendor | 45 | N/A | Code ↗Source ↗ | Looks wrong? |
| 98 | Phi 3 mini 128k instruct | vendor | 43.86 | N/A | Code ↗Source ↗ | Looks wrong? |
| 99 | Qwen2.5 3B | vendor | 43.73 | N/A | Code ↗Source ↗ | Looks wrong? |
| 100 | MAmmoTH2 8B Plus | vendor | 43.35 | N/A | Code ↗Source ↗ | Looks wrong? |
| 101 | Yi 34B | vendor | 43.03 | N/A | Code ↗Source ↗ | Looks wrong? |
| 102 | Mathstral 7B v0.1 | vendor | 42 | N/A | Code ↗Source ↗ | Looks wrong? |
| 103 | MiMo 7B Base | vendor | 41.9 | N/A | Code ↗Source ↗ | Looks wrong? |
| 104 | DeepSeek Coder V2 Lite Instruct | vendor | 41.57 | N/A | Code ↗Source ↗ | Looks wrong? |
| 105 | Mixtral 8x7B v0.1 | vendor | 41.03 | N/A | Code ↗Source ↗ | Looks wrong? |
| 106 | Meta Llama 3 8B Instruct | vendor | 40.98 | N/A | Code ↗Source ↗ | Looks wrong? |
| 107 | MAmmoTH2 7B Plus | vendor | 40.85 | N/A | Code ↗Source ↗ | Looks wrong? |
| 108 | Qwen2 7B | vendor | 40.73 | N/A | Code ↗Source ↗ | Looks wrong? |
| 109 | Mistral Nemo Base 2407 | vendor | 39.77 | N/A | Code ↗Source ↗ | Looks wrong? |
| 110 | EXAONE 3.5 2.4B Instruct | vendor | 39.1 | N/A | Code ↗Source ↗ | Looks wrong? |
| 111 | Yi 1.5 6B Chat | vendor | 38.23 | N/A | Code ↗Source ↗ | Looks wrong? |
| 112 | Qwen1.5 14B Chat | vendor | 38.02 | N/A | Code ↗Source ↗ | Looks wrong? |
| 113 | Ministral 8B Instruct 2410 | vendor | 37.93 | N/A | Code ↗Source ↗ | Looks wrong? |
| 114 | c4ai command r v01 | vendor | 37.9 | N/A | Code ↗Source ↗ | Looks wrong? |
| 115 | internlm2 math plus 20b | vendor | 37.1 | N/A | Code ↗Source ↗ | Looks wrong? |
| 116 | LLaDA 8B Instruct | vendor | 37 | N/A | Code ↗Source ↗ | Looks wrong? |
| 117 | Llama 3 Smaug 8B | vendor | 36.93 | N/A | Code ↗Source ↗ | Looks wrong? |
| 118 | Llama 3.1 8B | vendor | 36.6 | N/A | Code ↗Source ↗ | Looks wrong? |
| 119 | Meta Llama 3 8B | vendor | 35.36 | N/A | Code ↗Source ↗ | Looks wrong? |
| 120 | deepseek math 7b instruct | vendor | 35.3 | N/A | Code ↗Source ↗ | Looks wrong? |
| 121 | DeepSeek Coder V2 Lite Base | vendor | 34.37 | N/A | Code ↗Source ↗ | Looks wrong? |
| 122 | aya expanse 8b | vendor | 33.74 | N/A | Code ↗Source ↗ | Looks wrong? |
| 123 | internlm2 math plus 7b | vendor | 33.5 | N/A | Code ↗Source ↗ | Looks wrong? |
| 124 | granite 3.1 8b base | vendor | 33.08 | N/A | Code ↗Source ↗ | Looks wrong? |
| 125 | Qwen2.5 1.5B | vendor | 32.1 | N/A | Code ↗Source ↗ | Looks wrong? |
| 126 | granite 3.0 8b base | vendor | 31.03 | N/A | Code ↗Source ↗ | Looks wrong? |
| 127 | Mistral 7B Instruct v0.2 | vendor | 30.84 | N/A | Code ↗Source ↗ | Looks wrong? |
| 128 | Mistral 7B v0.2 | vendor | 30.43 | N/A | Code ↗Source ↗ | Looks wrong? |
| 129 | Qwen1.5 7B Chat | vendor | 29.06 | N/A | Code ↗Source ↗ | Looks wrong? |
| 130 | Yi 6B Chat | vendor | 28.84 | N/A | Code ↗Source ↗ | Looks wrong? |
| 131 | Yi 6B | vendor | 26.51 | N/A | Code ↗Source ↗ | Looks wrong? |
| 132 | granite 3.1 2b base | vendor | 23.89 | N/A | Code ↗Source ↗ | Looks wrong? |
| 133 | llemma 7b | vendor | 23.45 | N/A | Code ↗Source ↗ | Looks wrong? |
| 134 | Qwen2 1.5B Instruct | vendor | 22.62 | N/A | Code ↗Source ↗ | Looks wrong? |
| 135 | Qwen2 1.5B | vendor | 22.56 | N/A | Code ↗Source ↗ | Looks wrong? |
| 136 | Llama 3.2 3B | vendor | 22.17 | N/A | Code ↗Source ↗ | Looks wrong? |
| 137 | granite 3.0 2b base | vendor | 21.72 | N/A | Code ↗Source ↗ | Looks wrong? |
| 138 | granite 3.1 3b a800m base | vendor | 20.39 | N/A | Code ↗Source ↗ | Looks wrong? |
| 139 | SmolLM2 1.7B | vendor | 18.31 | N/A | Code ↗Source ↗ | Looks wrong? |
| 140 | Qwen2 0.5B | vendor | 14.97 | N/A | Code ↗Source ↗ | Looks wrong? |
| 141 | Qwen2.5 0.5B | vendor | 14.92 | N/A | Code ↗Source ↗ | Looks wrong? |
| 142 | granite 3.1 1b a400m base | vendor | 12.34 | N/A | Code ↗Source ↗ | Looks wrong? |
| 143 | Llama 3.2 1B | vendor | 11.95 | N/A | Code ↗Source ↗ | Looks wrong? |
| 144 | SmolLM2 360M | vendor | 11.38 | N/A | Code ↗Source ↗ | Looks wrong? |
| 145 | SmolLM2 135M | vendor | 10.85 | N/A | Code ↗Source ↗ | Looks wrong? |
| 146 | Qwen2.5 VL 72B Instruct | vendor | 0.65 | N/A | Code ↗Source ↗ | Looks wrong? |