| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Understanding | MMMU-Pro std. | Accuracy61.3 | 18 | |
| Multimodal Understanding | MMMU-Pro Vis | Score57.5 | 11 | |
| Massive Multi-discipline Multimodal Understanding | MMMU-Pro (V) | MMMU-Pro Score18.6 | 10 | |
| General VQA | MMMU-Pro standard | Score50.7 | 5 | |
| Medical Multi-discipline Multimodal Understanding | MMMU Pro Med | Pass@173.88 | 4 |