# AA-MMMU-Pro leaderboard

Multimodal & Grounded 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/multimodal-grounded-aa-mmmu-pro

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

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Image + text question answering |
| Tasks | Multimodal academic reasoning |
| Difficulty | Frontier multimodal |
| Published by | [Artificial Analysis MMMU-Pro Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/mmmu-pro) |

An Artificial Analysis MMMU-Pro score.

## AA-MMMU-Pro ranking

117 models with a published AA-MMMU-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 | Image + text question answering | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6.2 Astra](https://modelchoice.dev/models/gpt-6-2-astra) | OpenAI | 89.5 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Opus 5.5](https://modelchoice.dev/models/claude-opus-5-5) | Anthropic | 87.7 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 86.9 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-6.1 Sol](https://modelchoice.dev/models/gpt-6-1-sol) | OpenAI | 86.0 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Gemini 3.8 Flash](https://modelchoice.dev/models/gemini-3-8-flash) | Google | 85.6 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Gemini 3.7 Flash](https://modelchoice.dev/models/gemini-3-7-flash) | Google | 85.5 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Opus 5](https://modelchoice.dev/models/claude-opus-5) | Anthropic | 84.7 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GPT-6.1 Terra](https://modelchoice.dev/models/gpt-6-1-terra) | OpenAI | 84.7 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Gemini 3.5 Flash](https://modelchoice.dev/models/gemini-3-5-flash) | Google | 84.3 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Kimi K3.1 Pro](https://modelchoice.dev/models/kimi-3-1-pro) | Moonshot AI | 83.9 | Observed 2026-11-21 · source benchlm:models |
| 11 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 83.4 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Gemini 3.6 Flash](https://modelchoice.dev/models/gemini-3-6-flash) | Google | 83.2 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-6 Sol](https://modelchoice.dev/models/gpt-6-sol) | OpenAI | 82.9 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Qwen3.8 Max Preview](https://modelchoice.dev/models/qwen3-8-max-preview) | Alibaba | 82.8 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Gemini 3.1 Pro](https://modelchoice.dev/models/gemini-3-1-pro) | Google | 82.4 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Inkling 2 Small](https://modelchoice.dev/models/inkling-2-small) | Thinking Machines Lab | 81.6 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Muse Spark Open](https://modelchoice.dev/models/muse-spark-open) | Meta | 80.9 | Observed 2026-11-21 · source benchlm:models |
| 18 | [GPT-5.6 Terra](https://modelchoice.dev/models/gpt-5-6-terra) | OpenAI | 80.7 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 80.5 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Muse Spark](https://modelchoice.dev/models/muse-spark) | Meta | 80.5 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Qwen3.7 Plus](https://modelchoice.dev/models/qwen3-7-plus) | Alibaba | 80.5 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Grok 4.5](https://modelchoice.dev/models/grok-4-5) | xAI | 80.4 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Gemini 3 Pro](https://modelchoice.dev/models/gemini-3-pro) | Google | 80.2 | Observed 2026-11-21 · source benchlm:models |
| 24 | [GPT-5.5](https://modelchoice.dev/models/gpt-5-5) | OpenAI | 79.9 | Observed 2026-11-21 · source benchlm:models |
| 25 | [GPT-6 Luna](https://modelchoice.dev/models/gpt-6-luna) | OpenAI | 79.7 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Kimi K2.6](https://modelchoice.dev/models/kimi-2-6) | Moonshot AI | 79.4 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Apodex 1.1](https://modelchoice.dev/models/apodex-1-1) | Apodex | 79.2 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Apodex 1.1 Mini](https://modelchoice.dev/models/apodex-1-1-mini) | Apodex | 79.2 | Observed 2026-11-21 · source benchlm:models |
| 29 | [MiniMax M3.1 Flash](https://modelchoice.dev/models/minimax-m3-1-flash) | MiniMax | 79.1 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Gemini 3.5 Flash-Lite](https://modelchoice.dev/models/gemini-3-5-flash-lite) | Google | 79.0 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Ling 3.0 Flash VL](https://modelchoice.dev/models/ling-3-0-flash-vl) | InclusionAI | 79.0 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Claude Opus 4.7](https://modelchoice.dev/models/claude-opus-4-7) | Anthropic | 78.8 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Claude Opus 4.7 (Adaptive)](https://modelchoice.dev/models/claude-opus-4-7-max) | Anthropic | 78.8 | Last good 2026-11-18 · source benchlm:models |
| 34 | [Gemini 3 Flash](https://modelchoice.dev/models/gemini-3-flash) | Google | 78.6 | Observed 2026-11-21 · source benchlm:models |
| 34 | [GPT-5.6 Luna](https://modelchoice.dev/models/gpt-5-6-luna) | OpenAI | 78.6 | Observed 2026-11-21 · source benchlm:models |
| 34 | [MiniMax M3](https://modelchoice.dev/models/minimax-m3) | MiniMax | 78.6 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Qwen3.8-Flash-Next](https://modelchoice.dev/models/qwen3-8-flash-next) | Alibaba | 78.6 | Observed 2026-11-21 · source benchlm:models |
| 38 | [GPT-5.3 Codex](https://modelchoice.dev/models/gpt-5-3-codex) | OpenAI | 78.5 | Observed 2026-11-21 · source benchlm:models |
| 39 | [GPT-5.4](https://modelchoice.dev/models/gpt-5-4) | OpenAI | 78.4 | Observed 2026-11-21 · source benchlm:models |
| 40 | [Grok 4.3](https://modelchoice.dev/models/grok-4-3) | xAI | 78.1 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 78.0 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Claude Sonnet 5](https://modelchoice.dev/models/claude-sonnet-5) | Anthropic | 77.3 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Qwen3.5 397B](https://modelchoice.dev/models/qwen3-5-397b) | Alibaba | 77.3 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Qwen3.5 397B (Reasoning)](https://modelchoice.dev/models/qwen3-5-397b-reasoning) | Alibaba | 77.3 | Last good 2026-11-18 · source benchlm:models |
| 45 | [DeepSeek V4.1 Flash 1017](https://modelchoice.dev/models/deepseek-v4-1-flash) | DeepSeek | 77.0 | Observed 2026-11-21 · source benchlm:models |
| 46 | [Mistral Large 4](https://modelchoice.dev/models/mistral-large-4) | Mistral | 76.4 | Last good 2026-10-23 · source benchlm:models |
| 46 | [Step 5 Preview](https://modelchoice.dev/models/step-5-preview) | StepFun | 76.4 | Observed 2026-11-21 · source benchlm:models |
| 48 | [GPT-5.2-Codex](https://modelchoice.dev/models/gpt-5-2-codex) | OpenAI | 76.3 | Observed 2026-11-21 · source benchlm:models |
| 48 | [Qwen3.8-27B](https://modelchoice.dev/models/qwen3-8-27b) | Alibaba | 76.3 | Observed 2026-11-21 · source benchlm:models |
| 50 | [GPT-5.1](https://modelchoice.dev/models/gpt-5-1) | OpenAI | 75.5 | Observed 2026-11-21 · source benchlm:models |
| 51 | [Claude Opus 4.6 (Adaptive)](https://modelchoice.dev/models/claude-opus-4-6-thinking) | Anthropic | 75.4 | Observed 2026-11-21 · source benchlm:models |
| 51 | [Kimi K2.5](https://modelchoice.dev/models/kimi-k2-5) | Moonshot AI | 75.4 | Observed 2026-11-21 · source benchlm:models |
| 51 | [Kimi K2.5 (Reasoning)](https://modelchoice.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 75.4 | Last good 2026-11-18 · source benchlm:models |
| 54 | [Step 3.7 Flash](https://modelchoice.dev/models/step-3-7-flash) | StepFun | 75.3 | Observed 2026-11-21 · source benchlm:models |
| 55 | [Qwen3.5-122B-A10B](https://modelchoice.dev/models/qwen3-5-122b-a10b) | Alibaba | 75.0 | Observed 2026-11-21 · source benchlm:models |
| 55 | [Qwen3.5-27B](https://modelchoice.dev/models/qwen3-5-27b) | Alibaba | 75.0 | Observed 2026-11-21 · source benchlm:models |
| 55 | [Qwen3.6-35B-A3B](https://modelchoice.dev/models/qwen3-6-35b-a3b) | Alibaba | 75.0 | Observed 2026-11-21 · source benchlm:models |
| 58 | [Gemini 2.5 Pro](https://modelchoice.dev/models/gemini-2-5-pro) | Google | 74.9 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Qwen3.6-27B](https://modelchoice.dev/models/qwen3-6-27b) | Alibaba | 74.6 | Observed 2026-11-21 · source benchlm:models |
| 60 | [GPT-5 (medium)](https://modelchoice.dev/models/gpt-5-medium) | OpenAI | 74.3 | Last good 2026-11-18 · source benchlm:models |
| 60 | [Muse Glimmer 30B](https://modelchoice.dev/models/muse-glimmer-30b) | Meta | 74.3 | Observed 2026-11-21 · source benchlm:models |
| 62 | [GPT-5](https://modelchoice.dev/models/gpt-5) | OpenAI | 74.2 | Observed 2026-11-21 · source benchlm:models |
| 62 | [GPT-5 (high)](https://modelchoice.dev/models/gpt-5-high) | OpenAI | 74.2 | Last good 2026-11-18 · source benchlm:models |
| 64 | [Claude Opus 4.5 Thinking](https://modelchoice.dev/models/claude-opus-4-5-thinking) | Anthropic | 74.0 | Observed 2026-11-21 · source benchlm:models |
| 64 | [Inkling-Small](https://modelchoice.dev/models/inkling-small) | Thinking Machines Lab | 74.0 | Observed 2026-11-21 · source benchlm:models |
| 66 | [Inkling](https://modelchoice.dev/models/inkling) | Thinking Machines Lab | 73.5 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Gemma 4 31B](https://modelchoice.dev/models/gemma-4-31b) | Google | 73.4 | Observed 2026-11-21 · source benchlm:models |
| 68 | [GPT-5.4 mini](https://modelchoice.dev/models/gpt-5-4-mini) | OpenAI | 73.3 | Observed 2026-11-21 · source benchlm:models |
| 69 | [MiMo-V2.6-Flash](https://modelchoice.dev/models/mimo-v2-6-flash) | Xiaomi | 73.1 | Observed 2026-11-21 · source benchlm:models |
| 70 | [GLM-5V-Turbo](https://modelchoice.dev/models/glm-5v-turbo) | Z.AI | 72.8 | Observed 2026-11-21 · source benchlm:models |
| 71 | [Qwen3.5-35B-A3B](https://modelchoice.dev/models/qwen3-5-35b-a3b) | Alibaba | 72.7 | Observed 2026-11-21 · source benchlm:models |
| 72 | [Claude Opus 4.6](https://modelchoice.dev/models/claude-opus-4-6) | Anthropic | 72.5 | Observed 2026-11-21 · source benchlm:models |
| 72 | [GPT-5.1-Codex](https://modelchoice.dev/models/gpt-5-1-codex) | OpenAI | 72.5 | Observed 2026-11-21 · source benchlm:models |
| 72 | [GPT-5.1-Codex-Max](https://modelchoice.dev/models/gpt-5-1-codex-max) | OpenAI | 72.5 | Observed 2026-11-21 · source benchlm:models |
| 75 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 71.2 | Observed 2026-11-21 · source benchlm:models |
| 76 | [Claude Sonnet 4.6](https://modelchoice.dev/models/claude-sonnet-4-6) | Anthropic | 70.6 | Observed 2026-11-21 · source benchlm:models |
| 77 | [o3](https://modelchoice.dev/models/o3) | OpenAI | 70.1 | Observed 2026-11-21 · source benchlm:models |
| 78 | [MiMo-V2-Omni](https://modelchoice.dev/models/mimo-v2-omni) | Xiaomi | 69.9 | Observed 2026-11-21 · source benchlm:models |
| 79 | [Gemma 4 12B](https://modelchoice.dev/models/gemma-4-12b) | Google | 69.7 | Observed 2026-11-21 · source benchlm:models |
| 80 | [Gemma 4 26B A4B](https://modelchoice.dev/models/gemma-4-26b-a4b) | Google | 69.2 | Observed 2026-11-21 · source benchlm:models |
| 80 | [o4-mini](https://modelchoice.dev/models/o4-mini) | OpenAI | 69.2 | Observed 2026-11-21 · source benchlm:models |
| 82 | [Grok 4](https://modelchoice.dev/models/grok-4) | xAI | 68.8 | Observed 2026-11-21 · source benchlm:models |
| 83 | [Claude 4.1 Opus Thinking](https://modelchoice.dev/models/claude-4-1-opus-thinking) | Anthropic | 67.9 | Last good 2026-11-18 · source benchlm:models |
| 84 | [Gemini 2.5 Flash](https://modelchoice.dev/models/gemini-2-5-flash) | Google | 65.5 | Observed 2026-11-21 · source benchlm:models |
| 85 | [GPT-5.4 nano](https://modelchoice.dev/models/gpt-5-4-nano) | OpenAI | 65.4 | Observed 2026-11-21 · source benchlm:models |
| 85 | [Qwen3.5-4B](https://modelchoice.dev/models/qwen3-5-4b) | Alibaba | 65.4 | Observed 2026-11-21 · source benchlm:models |
| 87 | [Mistral Medium 3.5 128B](https://modelchoice.dev/models/mistral-medium-3-5-128b) | Mistral | 64.9 | Observed 2026-11-21 · source benchlm:models |
| 88 | [Grok 4.1 Fast (Reasoning)](https://modelchoice.dev/models/grok-4-1-fast-reasoning) | xAI | 63.3 | Observed 2026-11-21 · source benchlm:models |
| 89 | [Command A+](https://modelchoice.dev/models/command-a-plus) | Cohere | 63.2 | Observed 2026-11-21 · source benchlm:models |
| 90 | [Claude 4 Sonnet](https://modelchoice.dev/models/claude-4-sonnet) | Anthropic | 62.4 | Observed 2026-11-21 · source benchlm:models |
| 91 | [Llama 4 Maverick](https://modelchoice.dev/models/llama-4-maverick) | Meta | 62.1 | Observed 2026-11-21 · source benchlm:models |
| 92 | [Grok 4 Fast (Reasoning)](https://modelchoice.dev/models/grok-4-fast-reasoning) | xAI | 61.8 | Observed 2026-11-21 · source benchlm:models |
| 93 | [GPT-4.1](https://modelchoice.dev/models/gpt-4-1) | OpenAI | 61.2 | Observed 2026-11-21 · source benchlm:models |
| 94 | [Qwen3-Omni-30B-A3B-Thinking](https://modelchoice.dev/models/qwen3-omni-30b-a3b-thinking) | Alibaba | 60.2 | Observed 2026-11-21 · source benchlm:models |
| 95 | [Claude 3.7 Sonnet](https://modelchoice.dev/models/claude-3-7-sonnet) | Anthropic | 60.1 | Observed 2026-11-21 · source benchlm:models |
| 96 | [GPT-4.1 mini](https://modelchoice.dev/models/gpt-4-1-mini) | OpenAI | 58.7 | Observed 2026-11-21 · source benchlm:models |
| 97 | [Mistral Small 4](https://modelchoice.dev/models/mistral-small-4) | Mistral | 56.8 | Observed 2026-11-21 · source benchlm:models |
| 97 | [Mistral Small 4 (Reasoning)](https://modelchoice.dev/models/mistral-small-4-reasoning) | Mistral | 56.8 | Last good 2026-11-18 · source benchlm:models |
| 99 | [Mistral Large 3](https://modelchoice.dev/models/mistral-large-3) | Mistral | 55.7 | Observed 2026-11-21 · source benchlm:models |
| 100 | [Qwen3-Omni-30B-A3B-Instruct](https://modelchoice.dev/models/qwen3-omni-30b-a3b-instruct) | Alibaba | 55.5 | Observed 2026-11-21 · source benchlm:models |
| 101 | [Gemini 1.5 Pro](https://modelchoice.dev/models/gemini-1-5-pro) | Google | 55.0 | Observed 2026-11-21 · source benchlm:models |
| 102 | [Gemini 2.5 Flash-Lite](https://modelchoice.dev/models/gemini-2-5-flash-lite) | Google | 54.0 | Observed 2026-11-21 · source benchlm:models |
| 103 | [Nemotron 3 Nano Omni 30B A3B](https://modelchoice.dev/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | 53.2 | Observed 2026-11-21 · source benchlm:models |
| 104 | [Mistral Medium 3](https://modelchoice.dev/models/mistral-medium-3) | Mistral | 53.0 | Observed 2026-11-21 · source benchlm:models |
| 105 | [Llama 4 Scout](https://modelchoice.dev/models/llama-4-scout) | Meta | 52.9 | Observed 2026-11-21 · source benchlm:models |
| 106 | [Gemma 4 E4B](https://modelchoice.dev/models/gemma-4-e4b) | Google | 51.4 | Observed 2026-11-21 · source benchlm:models |
| 107 | [Gemini 1.5 Flash](https://modelchoice.dev/models/gemini-1-5-flash) | Google | 48.4 | Observed 2026-11-21 · source benchlm:models |
| 107 | [Grok 4.1 Fast](https://modelchoice.dev/models/grok-4-1-fast) | xAI | 48.4 | Observed 2026-11-21 · source benchlm:models |
| 109 | [Gemma 3 27B](https://modelchoice.dev/models/gemma-3-27b) | Google | 48.0 | Observed 2026-11-21 · source benchlm:models |
| 110 | [Claude 3.5 Haiku](https://modelchoice.dev/models/claude-3-5-haiku) | Anthropic | 45.6 | Observed 2026-11-21 · source benchlm:models |
| 111 | [Gemma 4 E2B](https://modelchoice.dev/models/gemma-4-e2b) | Google | 44.6 | Observed 2026-11-21 · source benchlm:models |
| 112 | [Nova Pro](https://modelchoice.dev/models/nova-pro) | Amazon | 44.3 | Observed 2026-11-21 · source benchlm:models |
| 113 | [GPT-4o mini](https://modelchoice.dev/models/gpt-4o-mini) | OpenAI | 41.5 | Observed 2026-11-21 · source benchlm:models |
| 114 | [GPT-4.1 nano](https://modelchoice.dev/models/gpt-4-1-nano) | OpenAI | 40.1 | Observed 2026-11-21 · source benchlm:models |
| 115 | [Claude 3 Haiku](https://modelchoice.dev/models/claude-3-haiku) | Anthropic | 30.8 | Observed 2026-11-21 · source benchlm:models |
| 116 | [LFM2.5-VL-1.6B-Extract](https://modelchoice.dev/models/lfm2-5-vl-1-6b-extract) | LiquidAI | 26.5 | Observed 2026-11-21 · source benchlm:models |
| 117 | [Phi-4 Multimodal Instruct](https://modelchoice.dev/models/phi-4-multimodal-instruct) | Microsoft | 14.5 | 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.
