# 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://modelscale.dev/leaderboards/benchmarks/multimodal-grounded-mmmu-pro

Massive Multi-discipline Multimodal Understanding Pro. Every model the catalog carries a published 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 | [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://arxiv.org/abs/2409.02813) |

A harder multimodal benchmark for frontier models that combines text with images, diagrams, charts, and academic visual reasoning tasks.

## MMMU-Pro ranking

60 models with a published 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-6.1 Terra](https://modelscale.dev/models/gpt-6-1-terra) | OpenAI | 85.5 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 84.1 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Gemini 3.1 Pro](https://modelscale.dev/models/gemini-3-1-pro) | Google | 83.9 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Gemini 3.5 Flash](https://modelscale.dev/models/gemini-3-5-flash) | Google | 83.6 | Observed 2026-11-21 · source benchlm:models |
| 5 | [GPT-5.6 Sol](https://modelscale.dev/models/gpt-5-6-sol) | OpenAI | 83 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | 82.3 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Inkling 2 Small](https://modelscale.dev/models/inkling-2-small) | Thinking Machines Lab | 81.6 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 81.6 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Seed 2.1 Pro](https://modelscale.dev/models/seed-2-1-pro) | ByteDance | 81.6 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-5.4](https://modelscale.dev/models/gpt-5-4) | OpenAI | 81.2 | Observed 2026-11-21 · source benchlm:models |
| 10 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | 81.2 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | 81 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-5.6 Terra](https://modelscale.dev/models/gpt-5-6-terra) | OpenAI | 80.7 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Muse Spark](https://modelscale.dev/models/muse-spark) | Meta | 80.4 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Seed 2.1 Turbo](https://modelscale.dev/models/seed-2-1-turbo) | ByteDance | 80.1 | Observed 2026-11-21 · source benchlm:models |
| 16 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | 79.5 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | 79.4 | Observed 2026-11-21 · source benchlm:models |
| 18 | [dots3-note Preview](https://modelscale.dev/models/dots3-note-preview) | Dots Studio | 79.1 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Qwen3.5 397B](https://modelscale.dev/models/qwen3-5-397b) | Alibaba | 79 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Qwen3.7 Plus](https://modelscale.dev/models/qwen3-7-plus) | Alibaba | 79 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | 78.8 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Hy4](https://modelscale.dev/models/hy4) | Tencent | 78.6 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Kimi K2.5](https://modelscale.dev/models/kimi-k2-5) | Moonshot AI | 78.5 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Kimi K2.5 (Reasoning)](https://modelscale.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 78.5 | Last good 2026-11-18 · source benchlm:models |
| 25 | [GPT-5.6 Luna](https://modelscale.dev/models/gpt-5-6-luna) | OpenAI | 78.4 | Observed 2026-11-21 · source benchlm:models |
| 26 | [Grok 4.3](https://modelscale.dev/models/grok-4-3) | xAI | 78.1 | Observed 2026-11-21 · source benchlm:models |
| 26 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | 78.1 | Observed 2026-11-21 · source benchlm:models |
| 28 | [Pareto 26.9](https://modelscale.dev/models/pareto-26-9) | Unbiased | 78 | Observed 2026-11-21 · source benchlm:models |
| 29 | [MiMo-V2.5](https://modelscale.dev/models/mimo-v2-5) | Xiaomi | 77.9 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Claude Opus 4.6](https://modelscale.dev/models/claude-opus-4-6) | Anthropic | 77.3 | Observed 2026-11-21 · source benchlm:models |
| 31 | [Gemma 4 31B](https://modelscale.dev/models/gemma-4-31b) | Google | 76.9 | Observed 2026-11-21 · source benchlm:models |
| 31 | [Qwen3.5-122B-A10B](https://modelscale.dev/models/qwen3-5-122b-a10b) | Alibaba | 76.9 | Observed 2026-11-21 · source benchlm:models |
| 33 | [GPT-5.4 mini](https://modelscale.dev/models/gpt-5-4-mini) | OpenAI | 76.6 | Observed 2026-11-21 · source benchlm:models |
| 34 | [Step 5 Preview](https://modelscale.dev/models/step-5-preview) | StepFun | 76 | Observed 2026-11-21 · source benchlm:models |
| 35 | [Hy4 flash](https://modelscale.dev/models/hy4-flash) | Tencent | 75.8 | Observed 2026-11-21 · source benchlm:models |
| 35 | [Qwen3.6-27B](https://modelscale.dev/models/qwen3-6-27b) | Alibaba | 75.8 | Observed 2026-11-21 · source benchlm:models |
| 37 | [Qwen3.6-35B-A3B](https://modelscale.dev/models/qwen3-6-35b-a3b) | Alibaba | 75.3 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Grok 4.20](https://modelscale.dev/models/grok-4-20-beta) | xAI | 75.2 | Observed 2026-11-21 · source benchlm:models |
| 39 | [Qwen3.5-35B-A3B](https://modelscale.dev/models/qwen3-5-35b-a3b) | Alibaba | 75.1 | Observed 2026-11-21 · source benchlm:models |
| 40 | [Qwen3.5-27B](https://modelscale.dev/models/qwen3-5-27b) | Alibaba | 75 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Inkling 2 Mini](https://modelscale.dev/models/inkling-2-mini) | Thinking Machines Lab | 74.9 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Inkling-Small](https://modelscale.dev/models/inkling-small) | Thinking Machines Lab | 74 | Observed 2026-11-21 · source benchlm:models |
| 42 | [Muse Glimmer 30B](https://modelscale.dev/models/muse-glimmer-30b) | Meta | 74 | Observed 2026-11-21 · source benchlm:models |
| 44 | [Gemma 4 26B A4B](https://modelscale.dev/models/gemma-4-26b-a4b) | Google | 73.8 | Observed 2026-11-21 · source benchlm:models |
| 45 | [Inkling](https://modelscale.dev/models/inkling) | Thinking Machines Lab | 73.5 | Observed 2026-11-21 · source benchlm:models |
| 46 | [Interfaze Beta](https://modelscale.dev/models/interfaze-beta) | Interfaze | 71.1 | Observed 2026-11-21 · source benchlm:models |
| 47 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 70.6 | Observed 2026-11-21 · source benchlm:models |
| 48 | [Gemma 4 12B](https://modelscale.dev/models/gemma-4-12b) | Google | 69.1 | Observed 2026-11-21 · source benchlm:models |
| 49 | [Qwen3-VL-235B-A22B Instruct](https://modelscale.dev/models/qwen3-vl-235b-a22b-instruct) | Alibaba | 68.1 | Observed 2026-11-21 · source benchlm:models |
| 50 | [GPT-5.4 nano](https://modelscale.dev/models/gpt-5-4-nano) | OpenAI | 66.1 | Observed 2026-11-21 · source benchlm:models |
| 51 | [GLM-4.6V](https://modelscale.dev/models/glm-4-6v) | Z.AI | 66 | Observed 2026-11-21 · source benchlm:models |
| 52 | [Command A+](https://modelscale.dev/models/command-a-plus) | Cohere | 63 | Observed 2026-11-21 · source benchlm:models |
| 53 | [GLM-4.6V-Flash](https://modelscale.dev/models/glm-4-6v-flash) | Z.AI | 60.6 | Observed 2026-11-21 · source benchlm:models |
| 54 | [MiniMax-VL-01](https://modelscale.dev/models/minimax-vl-01) | MiniMax | 52.7 | Observed 2026-11-21 · source benchlm:models |
| 55 | [Gemma 4 E4B](https://modelscale.dev/models/gemma-4-e4b) | Google | 52.6 | Observed 2026-11-21 · source benchlm:models |
| 56 | [Qwen2.5-VL-32B](https://modelscale.dev/models/qwen2-5-vl-32b) | Alibaba | 49.5 | Observed 2026-11-21 · source benchlm:models |
| 57 | [Mistral Small 3.1](https://modelscale.dev/models/mistral-small-3-1) | Mistral | 49.25 | Observed 2026-11-21 · source benchlm:models |
| 58 | [LFM3-VL-2B](https://modelscale.dev/models/lfm3-vl-2b) | LiquidAI | 45.7 | Observed 2026-11-21 · source benchlm:models |
| 59 | [Gemma 4 E2B](https://modelscale.dev/models/gemma-4-e2b) | Google | 44.2 | Observed 2026-11-21 · source benchlm:models |
| 60 | [LFM2.5-VL-3B](https://modelscale.dev/models/lfm2-5-vl-3b) | LiquidAI | 30.5 | 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.
