| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AURORA-BENCH All (test) | SmartEdit (SE) | Human Eval Score-0.23 | 4 | 1mo ago | |
| Kubric (test) | C-FDM | Human Evaluation Score0.4 | 4 | 1mo ago | |
| WhatsUp (test) | Ground Truth (GoT) | Human Evaluation Score0.25 | 4 | 1mo ago | |
| Something-Something (test) | C-FDM | Human Evaluation Score0.2 | 4 | 1mo ago | |
| Action-Genome (test) | C-FDM | Human Evaluation Score0.37 | 4 | 1mo ago |
