Jailbreak Attack on AdvBench (ASR, Avg.Score)
0Attack Success Rate (ASR)
PAIR
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 0 | 0 | |
2026.02 | 0 | 0 | |
2026.02 | 0 | 0.02 | |
2026.02 | 0 | 0 | |
2026.02 | 0 | 0 | |
2026.02 | 0 | 0.04 | |
2026.02 | 2 | 0.06 | |
2026.02 | 2 | 0.06 | |
2026.02 | 4 | 0.12 | |
2026.02 | 6 | 0.24 | |
2026.02 | 8 | 0.24 | |
2026.04 | 8.5 | - | |
2026.02 | 12 | 0.4 | |
2026.02 | 12 | 0.4 | |
| 12.1 | - | ||
2026.02 | 14 | 0.52 | |
2026.04 | 14.2 | - | |
2026.04 | 16.4 | - | |
| 18.5 | - | ||
2026.02 | 24 | 1.04 | |
2026.02 | 28 | 1.22 | |
| 30.3 | - | ||
2026.02 | 40 | 1.86 | |
2026.02 | 40 | 1.6 | |
2026.02 | 44 | 2.04 | |
2026.02 | 50 | 1.9 | |
2026.02 | 50 | 2 | |
2026.02 | 52 | 2.1 | |
2026.02 | 54 | 2.04 | |
2026.02 | 70 | 2.52 | |
2026.02 | 74 | 2.88 | |
2026.02 | 74 | 3.06 | |
2026.02 | 78 | 2.64 | |
2026.02 | 80 | 2.6 | |
2026.02 | 84 | 3.1 | |
2026.02 | 84 | 4 | |
2026.02 | 88 | 3.18 | |
2026.02 | 88 | 3.36 | |
2026.02 | 88 | 3.32 | |
2026.02 | 88 | 4 | |
2026.02 | 92 | 4.52 | |
2026.02 | 98 | 4.3 | |
2026.02 | 100 | 4.82 | |
2026.02 | 100 | 3.14 | |
2026.02 | 100 | 4.74 | |
2026.02 | 100 | 4.84 | |
2026.02 | 100 | 4.88 | |
2026.02 | 100 | 4.76 |