Safety on WildJailbreak
17.6Harmful Response Ratio
STAR-1
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 17.6 | - | |
2026.01 | 21.15 | - | |
2026.01 | 30.85 | - | |
2026.01 | 32.6 | - | |
2026.01 | 35.4 | - | |
2026.01 | 40.5 | - | |
2026.01 | 42.45 | - | |
2026.01 | 45.75 | - | |
2026.01 | 45.85 | - | |
2026.01 | 46.95 | - | |
2026.01 | 47.65 | - | |
2026.01 | 48.75 | - | |
2026.01 | 49.65 | - | |
2026.01 | 49.7 | - | |
2026.01 | 50.2 | - | |
2026.01 | 50.2 | - | |
2026.01 | 50.45 | - | |
2026.01 | 51.55 | - | |
2026.01 | 51.8 | - | |
2026.01 | 52.65 | - | |
2026.01 | 53.15 | - | |
2026.02 | - | 56.8 | |
2026.02 | - | 48.8 | |
2026.02 | - | 98.8 | |
2026.02 | - | 95.6 | |
2026.02 | - | 100 | |
2026.02 | - | 91.2 | |
2026.02 | - | 97.2 | |
2026.02 | - | 100 | |
2026.01 | - | 91.6 | |
2026.01 | - | 49.6 | |
| - | 91.1 | ||
2026.01 | - | 76.8 |