# Massive Multi-discipline Multimodal Understanding (MMMU)

> A broad multimodal reasoning benchmark spanning charts, diagrams, tables, and academic visual question answering.

Canonical page: https://benchlm.ai/benchmarks/mmmu

- Category: [Multimodal & Grounded](/multimodal-grounded)
- Last updated: October 7, 2026

## About MMMU

- Year: 2024
- Tasks: Multimodal academic reasoning
- Format: Image + text question answering
- Difficulty: Frontier multimodal
- Paper: [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://arxiv.org/abs/2401.05508)

MMMU is the base benchmark family behind later MMMU-Pro variants. It measures whether a model can answer expert-style questions that require combining visual understanding with domain knowledge and reasoning.

MMMU is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (11 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Qwen3.6 Plus](/models/qwen3-6-plus) | Alibaba | 86.0% |
| 2 | [Qwen3.5-122B-A10B](/models/qwen3-5-122b-a10b) | Alibaba | 83.9% |
| 3 | [Qwen3.6-27B](/models/qwen3-6-27b) | Alibaba | 82.9% |
| 4 | [Qwen3.5-27B](/models/qwen3-5-27b) | Alibaba | 82.3% |
| 5 | [Qwen3.6-35B-A3B](/models/qwen3-6-35b-a3b) | Alibaba | 81.7% |
| 6 | [Qwen3.5-35B-A3B](/models/qwen3-5-35b-a3b) | Alibaba | 81.4% |
| 7 | [Command A+](/models/command-a-plus) | Cohere | 75.1% |
| 8 | [Nemotron 3 Nano Omni 30B A3B](/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | 70.8% |
| 9 | [LFM2.5-VL-3B](/models/lfm2-5-vl-3b) | LiquidAI | 48.4% |
| 10 | [ZAYA1-VL-8B](/models/zaya1-vl-8b) | Zyphra | 46.0% |
| 11 | [LFM2.5-VL-450M](/models/lfm2-5-vl-450m) | LiquidAI | 32.7% |

## FAQ

### What does MMMU measure?

A broad multimodal reasoning benchmark spanning charts, diagrams, tables, and academic visual question answering.

### Which model scores highest on MMMU?

Qwen3.6 Plus by Alibaba currently leads with a score of 86.0% on MMMU.

### How many models are evaluated on MMMU?

11 AI models have published results on MMMU in the BenchLM catalog.

### Does MMMU affect BenchLM's overall score?

Not directly. MMMU is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on MMMU

- [Qwen3.6 Plus vs Qwen3.5-122B-A10B](/compare/qwen3-5-122b-a10b-vs-qwen3-6-plus)
- [Qwen3.5-122B-A10B vs Qwen3.6-27B](/compare/qwen3-5-122b-a10b-vs-qwen3-6-27b)
- [Qwen3.6-27B vs Qwen3.5-27B](/compare/qwen3-5-27b-vs-qwen3-6-27b)
- [Qwen3.5-27B vs Qwen3.6-35B-A3B](/compare/qwen3-5-27b-vs-qwen3-6-35b-a3b)