| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Cleaned-PKU-HH-SafeRLHF (test) | Reward Accuracy91.8 | 15 | 7d ago | ||
| ManiSkill 4-task (Color Swapped OOD) | ReCouPLe-EC | Pick Accuracy77.3 | 5 | 2mo ago | |
| ManiSkill 4-task In Distribution | ReCouPLe-EC | Pick Reward Accuracy100 | 5 | 2mo ago | |
| ManiSkill 2-task Color Swapped OOD | ReCouPLe-EC | Pick Reward Accuracy82 | 5 | 2mo ago | |
| ManiSkill In Distribution 2 | ReCouPLe-EC | Reward Accuracy (Pick)99.3 | 5 | 2mo ago |
