| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Capability Evaluation | MM-Star | Average Score60.6 | 36 | |
| Comprehensive reasoning | MM-Star | Accuracy62 | 18 | |
| Complex Multimodal Reasoning | MM-Star | Reasoning Score55.44 | 10 | |
| Visual reasoning | MM-Star (test) | Accuracy69.1 | 9 |