Benchmark
MMMU (val)
vision
multimodal
reasoning
general
multimodal
Validation set of the Massive Multi-discipline Multimodal Understanding and Reasoning benchmark. Features college-level multimodal questions across 6 core disciplines (Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, Tech & Engineering) spanning 30 subjects and 183 subfields with diverse image types including charts, diagrams, maps, and tables.
语言EN
满分1
参评模型3
模型排名
| 名次 | 模型 | 机构 | 分数 | 来源 |
|---|---|---|---|---|
| 1 | Gemma 3 27B | 64.9 | 来源 ↗ | |
| 2 | Gemma 3 12B | 59.6 | 来源 ↗ | |
| 3 | Gemma 3 4B | 48.8 | 来源 ↗ |