# AA 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://modelscale.dev/leaderboards/benchmarks/knowledge-aa-mmlu-pro

Artificial Analysis MMLU-Pro. Every model the catalog carries a published AA MMLU-Pro value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Knowledge |
| Measure | Accuracy |
| Tasks | Professional multi-subject questions |
| Difficulty | Professional knowledge and reasoning |
| Published by | [Artificial Analysis MMLU-Pro Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/mmlu-pro) |

An independently evaluated MMLU-Pro result from Artificial Analysis.

## AA MMLU-Pro ranking

18 models with a published AA 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 | Accuracy | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | 89.8 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Opus 4.5 Thinking](https://modelscale.dev/models/claude-opus-4-5-thinking) | Anthropic | 89.5 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 88.9 | Last good 2026-10-23 · source benchlm:models |
| 4 | [Claude 4.1 Opus Thinking](https://modelscale.dev/models/claude-4-1-opus-thinking) | Anthropic | 88.0 | Last good 2026-11-18 · source benchlm:models |
| 5 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | 87.4 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Claude 4 Opus Thinking](https://modelscale.dev/models/claude-4-opus-thinking) | Anthropic | 87.3 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GPT-5](https://modelscale.dev/models/gpt-5) | OpenAI | 87.1 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GPT-5 (high)](https://modelscale.dev/models/gpt-5-high) | OpenAI | 87.1 | Last good 2026-11-18 · source benchlm:models |
| 9 | [GPT-5.1](https://modelscale.dev/models/gpt-5-1) | OpenAI | 87.0 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Grok 4](https://modelscale.dev/models/grok-4) | xAI | 86.6 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Gemini 2.5 Pro](https://modelscale.dev/models/gemini-2-5-pro) | Google | 86.2 | Observed 2026-11-21 · source benchlm:models |
| 12 | [GLM-4.7](https://modelscale.dev/models/glm-4-7) | Z.AI | 85.6 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Grok 4.1 Fast (Reasoning)](https://modelscale.dev/models/grok-4-1-fast-reasoning) | xAI | 85.4 | Observed 2026-11-21 · source benchlm:models |
| 14 | [o3](https://modelscale.dev/models/o3) | OpenAI | 85.3 | Observed 2026-11-21 · source benchlm:models |
| 15 | [DeepSeek V3.1 (Reasoning)](https://modelscale.dev/models/deepseek-v3-1-reasoning) | DeepSeek | 85.1 | Last good 2026-11-18 · source benchlm:models |
| 16 | [Grok 4 Fast (Reasoning)](https://modelscale.dev/models/grok-4-fast-reasoning) | xAI | 85.0 | Observed 2026-11-21 · source benchlm:models |
| 17 | [DeepSeek-R1](https://modelscale.dev/models/deepseek-r1) | DeepSeek | 84.9 | Observed 2026-11-21 · source benchlm:models |
| 18 | [GPT-OSS 120B](https://modelscale.dev/models/gpt-oss-120b) | OpenAI | 80.8 | Last good 2026-09-22 · 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.
