| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Safety Gymnasium | DT + SAS | Reward0.76 | 9 | 2mo ago | |
| Bullet-Safety-Gym OSRL | CDT | Reward0.84 | 9 | 5mo ago | |
| Bullet Gym | Normalized Reward0.84 | 6 | 2mo ago | ||
| Bullet Safety Gym eval environment | TRPO-Saute | Reward447.1 | 4 | 24d ago | |
| Bullet-Safety-Gym | CDT+SAS | Normalized Reward38 | 2 | 2mo ago |