# MMLU-Pro leaderboard

Knowledge benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/knowledge-mmlu-pro

Massive Multitask Language Understanding Professional. Every model the catalog carries a published MMLU-Pro value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Knowledge |
| Measure | 10-way multiple choice |
| Tasks | Multiple subjects |
| Difficulty | Professional level |
| Published by | [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://arxiv.org/abs/2406.01574) |

An enhanced version of MMLU with 10 answer choices instead of 4, featuring more reasoning-focused questions that better differentiate frontier models.

## MMLU-Pro ranking

77 models with a published MMLU-Pro value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | 10-way multiple choice | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Qwen3.7 Max](https://modelchoice.dev/models/qwen3-7-max) | Alibaba | 89.6 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 89.5 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 88.5 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Qwen3.7 Plus](https://modelchoice.dev/models/qwen3-7-plus) | Alibaba | 88.5 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Qwen3.5 397B](https://modelchoice.dev/models/qwen3-5-397b) | Alibaba | 87.8 | Observed 2026-11-21 · source benchlm:models |
| 6 | [DeepSeek V4 Pro](https://modelchoice.dev/models/deepseek-v4-pro) | DeepSeek | 87.5 | Observed 2026-11-21 · source benchlm:models |
| 6 | [DeepSeek V4 Pro 0813](https://modelchoice.dev/models/deepseek-v4-pro-max) | DeepSeek | 87.5 | Last good 2026-11-18 · source benchlm:models |
| 8 | [Kimi K2.5](https://modelchoice.dev/models/kimi-k2-5) | Moonshot AI | 87.1 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Kimi K2.5 (Reasoning)](https://modelchoice.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 87.1 | Last good 2026-11-18 · source benchlm:models |
| 10 | [Nemotron 3 Ultra](https://modelchoice.dev/models/nemotron-3-ultra-500b) | NVIDIA | 86.8 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Qwen3.5-122B-A10B](https://modelchoice.dev/models/qwen3-5-122b-a10b) | Alibaba | 86.7 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Solar Pro 4](https://modelchoice.dev/models/solar-pro-4) | Upstage | 86.3 | Observed 2026-11-21 · source benchlm:models |
| 13 | [DeepSeek V4 Flash 0731](https://modelchoice.dev/models/deepseek-v4-flash-max) | DeepSeek | 86.2 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Qwen3.6-27B](https://modelchoice.dev/models/qwen3-6-27b) | Alibaba | 86.2 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Solar Open 2](https://modelchoice.dev/models/solar-open-2) | Upstage | 86.2 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Qwen3.5-27B](https://modelchoice.dev/models/qwen3-5-27b) | Alibaba | 86.1 | Observed 2026-11-21 · source benchlm:models |
| 17 | [GLM-5](https://modelchoice.dev/models/glm-5) | Z.AI | 85.7 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Qwen3.5-35B-A3B](https://modelchoice.dev/models/qwen3-5-35b-a3b) | Alibaba | 85.3 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Gemma 4 31B](https://modelchoice.dev/models/gemma-4-31b) | Google | 85.2 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Qwen3.6-35B-A3B](https://modelchoice.dev/models/qwen3-6-35b-a3b) | Alibaba | 85.2 | Observed 2026-11-21 · source benchlm:models |
| 21 | [DeepSeek-R1-0528](https://modelchoice.dev/models/deepseek-r1-0528) | DeepSeek | 85 | Observed 2026-11-21 · source benchlm:models |
| 21 | [MAI-Thinking-1](https://modelchoice.dev/models/mai-thinking-1) | Microsoft | 85 | Observed 2026-11-21 · source benchlm:models |
| 23 | [MiMo-V2-Flash](https://modelchoice.dev/models/mimo-v2-flash) | Xiaomi | 84.9 | Observed 2026-11-21 · source benchlm:models |
| 24 | [DeepSeek V3.1 (Reasoning)](https://modelchoice.dev/models/deepseek-v3-1-reasoning) | DeepSeek | 84.8 | Last good 2026-11-18 · source benchlm:models |
| 25 | [Qwen3 235B 2507 (Reasoning)](https://modelchoice.dev/models/qwen3-235b-2507-reasoning) | Alibaba | 84.4 | Last good 2026-11-18 · source benchlm:models |
| 26 | [GLM-4.7](https://modelchoice.dev/models/glm-4-7) | Z.AI | 84.3 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Ripple-65B Preview](https://modelchoice.dev/models/ripple-65b-preview) | Ricursive Intelligence | 84.2 | Observed 2026-11-21 · source benchlm:models |
| 28 | [DeepSeek-R1](https://modelchoice.dev/models/deepseek-r1) | DeepSeek | 84 | Observed 2026-11-21 · source benchlm:models |
| 29 | [Nemotron 3 Super 100B](https://modelchoice.dev/models/nemotron-3-super-100b) | NVIDIA | 83.73 | Observed 2026-11-21 · source benchlm:models |
| 30 | [DeepSeek V3.1](https://modelchoice.dev/models/deepseek-v3-1) | DeepSeek | 83.7 | Observed 2026-11-21 · source benchlm:models |
| 31 | [K-EXAONE 2.0](https://modelchoice.dev/models/k-exaone-2-0) | LG AI Research | 83.5 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Qwen3 235B 2507](https://modelchoice.dev/models/qwen3-235b-2507) | Alibaba | 83 | Observed 2026-11-21 · source benchlm:models |
| 33 | [Gemma 4 26B A4B](https://modelchoice.dev/models/gemma-4-26b-a4b) | Google | 82.6 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Claude Opus 4.6](https://modelchoice.dev/models/claude-opus-4-6) | Anthropic | 82 | Observed 2026-11-21 · source benchlm:models |
| 35 | [Exaone 4.0 32B](https://modelchoice.dev/models/exaone-4-0-32b) | LG AI Research | 81.8 | Observed 2026-11-21 · source benchlm:models |
| 36 | [Sarvam 105B](https://modelchoice.dev/models/sarvam-105b) | Sarvam | 81.7 | Observed 2026-11-21 · source benchlm:models |
| 37 | [Nemotron 3.5 Lightning 30B A3B NVFP4](https://modelchoice.dev/models/nemotron-3-5-lightning-30b-a3b-nvfp4) | NVIDIA | 81.62 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Kimi K2](https://modelchoice.dev/models/kimi-k2) | Moonshot AI | 81.1 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Sarvam 30B](https://modelchoice.dev/models/sarvam-30b) | Sarvam | 80 | Observed 2026-11-21 · source benchlm:models |
| 40 | [Grok 3 [Beta]](https://modelchoice.dev/models/grok-3-beta) | xAI | 79.9 | Observed 2026-11-21 · source benchlm:models |
| 41 | [LongCat-Flash-Lite-Sparse](https://modelchoice.dev/models/longcat-flash-lite-sparse) | Meituan | 79.24 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Claude Sonnet 4.6](https://modelchoice.dev/models/claude-sonnet-4-6) | Anthropic | 79.2 | Observed 2026-11-21 · source benchlm:models |
| 43 | [Nemotron 3 Nano 30B](https://modelchoice.dev/models/nemotron-3-nano-30b) | NVIDIA | 78.3 | Observed 2026-11-21 · source benchlm:models |
| 44 | [Granite 4.2 30B](https://modelchoice.dev/models/granite-4-2-30b) | IBM | 77.6 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Nemotron 3 Nano Omni 30B A3B](https://modelchoice.dev/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | 77.3 | Observed 2026-11-21 · source benchlm:models |
| 46 | [Gemma 4 12B](https://modelchoice.dev/models/gemma-4-12b) | Google | 77.2 | Observed 2026-11-21 · source benchlm:models |
| 47 | [Qwen2.5-Max](https://modelchoice.dev/models/qwen2-5-max) | Alibaba | 76.1 | Observed 2026-11-21 · source benchlm:models |
| 48 | [Phi-4-reasoning-plus](https://modelchoice.dev/models/phi-4-reasoning-plus) | Microsoft | 76 | Observed 2026-11-21 · source benchlm:models |
| 49 | [Celeris-1](https://modelchoice.dev/models/celeris-1) | Celeris | 75.9 | Observed 2026-11-21 · source benchlm:models |
| 49 | [DeepSeek V3](https://modelchoice.dev/models/deepseek-v3) | DeepSeek | 75.9 | Observed 2026-11-21 · source benchlm:models |
| 51 | [MiniMax-Text-01](https://modelchoice.dev/models/minimax-text-01) | MiniMax | 75.7 | Observed 2026-11-21 · source benchlm:models |
| 52 | [Grok 2](https://modelchoice.dev/models/grok-2) | xAI | 75.5 | Observed 2026-11-21 · source benchlm:models |
| 53 | [Phi-4-reasoning](https://modelchoice.dev/models/phi-4-reasoning) | Microsoft | 74.3 | Observed 2026-11-21 · source benchlm:models |
| 54 | [ZAYA1-8B](https://modelchoice.dev/models/zaya1-8b) | Zyphra | 74.2 | Observed 2026-11-21 · source benchlm:models |
| 55 | [Granite 4.2 8B](https://modelchoice.dev/models/granite-4-2-8b) | IBM | 74.04 | Observed 2026-11-21 · source benchlm:models |
| 56 | [Grok 2 mini](https://modelchoice.dev/models/grok-2-mini) | xAI | 72 | Observed 2026-11-21 · source benchlm:models |
| 57 | [MiniCPM5-2B](https://modelchoice.dev/models/minicpm5-2b) | OpenBMB | 70.8 | Observed 2026-11-21 · source benchlm:models |
| 58 | [Gemma 4 E4B](https://modelchoice.dev/models/gemma-4-e4b) | Google | 69.4 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Llama 3.3 70B](https://modelchoice.dev/models/llama-3-3-70b) | Meta | 68.9 | Observed 2026-11-21 · source benchlm:models |
| 60 | [Qwen2.5-VL-32B](https://modelchoice.dev/models/qwen2-5-vl-32b) | Alibaba | 68.8 | Observed 2026-11-21 · source benchlm:models |
| 61 | [ZAYA1-74B-Preview](https://modelchoice.dev/models/zaya1-74b-preview) | Zyphra | 68.1 | Observed 2026-11-21 · source benchlm:models |
| 62 | [Granite 4.2 3B](https://modelchoice.dev/models/granite-4-2-3b) | IBM | 67.84 | Observed 2026-11-21 · source benchlm:models |
| 63 | [Mistral Small 3.1](https://modelchoice.dev/models/mistral-small-3-1) | Mistral | 66.76 | Observed 2026-11-21 · source benchlm:models |
| 64 | [Llama 3.1 70B](https://modelchoice.dev/models/llama-3-1-70b) | Meta | 66.4 | Observed 2026-11-21 · source benchlm:models |
| 65 | [Claude 3.5 Haiku](https://modelchoice.dev/models/claude-3-5-haiku) | Anthropic | 65 | Observed 2026-11-21 · source benchlm:models |
| 66 | [Gemma 4 E2B](https://modelchoice.dev/models/gemma-4-e2b) | Google | 60 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Soofi S 30B-A3B](https://modelchoice.dev/models/soofi-s-30b-a3b) | Soofi Project | 51.4 | Observed 2026-11-21 · source benchlm:models |
| 68 | [MiniCPM5-1B](https://modelchoice.dev/models/minicpm5-1b) | OpenBMB | 48.85 | Observed 2026-11-21 · source benchlm:models |
| 69 | [Llama 3.1 8B](https://modelchoice.dev/models/llama-3-1-8b) | Meta | 48.3 | Observed 2026-11-21 · source benchlm:models |
| 70 | [Phi-3.5-mini](https://modelchoice.dev/models/phi-3-5-mini) | Microsoft | 47.4 | Observed 2026-11-21 · source benchlm:models |
| 71 | [Granite-4.0-1B](https://modelchoice.dev/models/granite-4-0-1b) | IBM | 34.02 | Observed 2026-11-21 · source benchlm:models |
| 72 | [Granite-4.0-H-1B](https://modelchoice.dev/models/granite-4-0-h-1b) | IBM | 32.86 | Observed 2026-11-21 · source benchlm:models |
| 73 | [LFM2.5-230M](https://modelchoice.dev/models/lfm2-5-230m) | LiquidAI | 20.25 | Observed 2026-11-21 · source benchlm:models |
| 74 | [LFM2.5-350M](https://modelchoice.dev/models/lfm2-5-350m) | LiquidAI | 20.01 | Observed 2026-11-21 · source benchlm:models |
| 75 | [LFM2.5-VL-450M](https://modelchoice.dev/models/lfm2-5-vl-450m) | LiquidAI | 19.32 | Observed 2026-11-21 · source benchlm:models |
| 76 | [Granite-4.0-H-350M](https://modelchoice.dev/models/granite-4-0-h-350m) | IBM | 14.38 | Observed 2026-11-21 · source benchlm:models |
| 77 | [Granite-4.0-350M](https://modelchoice.dev/models/granite-4-0-350m) | IBM | 12.13 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
