| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TruthfulQA | F-DPO | MC1 Accuracy58.5 | 83 | 5d ago | |
| ReCoRD | SubZero-GV (LoRA) | Accuracy83.8 | 29 | 1mo ago | |
| MSRVTT (test) | InternVideo | Accuracy93.4 | 15 | 1mo ago | |
| COPA | Accuracy100 | 12 | 1mo ago | ||
| MSR-VTT | InternVideo | Accuracy93.5 | 11 | 1mo ago | |
| LSMDC 2016 (test) | CT-SAN | Accuracy67 | 11 | 1mo ago | |
| A-OKVQA 1.0 (test) | Prophet++ | Accuracy86.7 | 9 | 1mo ago | |
| A-OKVQA 1.0 (val) | Prophet++ | Accuracy87.7 | 9 | 1mo ago | |
| LSMDC | All-in-one | Accuracy84.4 | 8 | 1mo ago | |
| ConFiQA MC | ContextFocus | Ps Score53.4 | 4 | 1mo ago | |
| Swag (test) | Accuracy80.85 | 3 | 1mo ago |