MMMU
Benchmark website →Massive Multi-discipline Multimodal Understanding — 11.5K expert-level questions across 30 subjects requiring college-level knowledge with images.
About this test
- What it measures
- Multimodal reasoning — understanding images, charts, diagrams alongside text for expert-level problems.
- How it was administered
- Multiple-choice and open-ended; requires processing images; accuracy metric across 6 core disciplines.
Model rankings
Models ranked by score on this benchmark. Higher is better.
| Rank | Model | Provider | Score | Percentile | Tags |
|---|