| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Wildjailbreak (Benign) | DPO | Wildjailbreak Benign Refusal Rate28.4 | 42 | 4d ago | |
| XSTest | CB | XSTest Score86.89 | 42 | 4d ago | |
| Over-refusal Evaluation Suite (XSTest, WildJailbreak, WildGuard, OKTest, OR-Bench) | XSTest Refusal Rate (%)3.2 | 24 | 4d ago |