| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Reasoning | MMT-Bench | Accuracy57.88 | 23 | |
| Multi-image Understanding | MMT-Bench (val) | Score71.8 | 23 | |
| Multimodal Understanding | MMT-Bench | Accuracy59.2 | 19 | |
| Multimodal Evaluation | MMT-Bench | Accuracy62.65 | 13 | |
| Multimodal tasks | MMT-Bench 1.0 (test) | Overall63.4 | 13 |