| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MSR-VTT (test) | LogicAgent | Accuracy Score3.67 | 14 | 3d ago | |
| WebQA (test) | LogicAgent | BLEURT0.623 | 14 | 3d ago | |
| Pororo (test) | LogicAgent | BLEURT Score45 | 14 | 3d ago | |
| MMIU (test) | LogicAgent | BLEURT Score0.306 | 14 | 3d ago | |
| Ego4D (test) | LogicAgent | BLEURT0.48 | 14 | 3d ago | |
| VIST (test) | LogicAgent | BLEURT0.456 | 14 | 3d ago | |
| BookSum oracle timing | CFPG | Average Score94 | 12 | 3d ago |