Multi-turn Jailbreaking on StrongReject (test)
0.34ASR
Siren
Updated 3mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 0.34 | 0.0197 | |
2026.01 | 0.61 | 0.0312 | |
2026.01 | 0.63 | 0.0373 | |
2026.01 | 0.63 | 0.0312 | |
2026.01 | 0.67 | 0.0342 | |
2026.01 | 0.67 | 0.0332 | |
2026.01 | 0.68 | 0.0308 | |
2026.01 | 0.68 | 0.0318 | |
2026.01 | 0.68 | 0.0292 | |
2026.01 | 0.68 | 0.0326 | |
2026.01 | 0.7 | 0.0325 | |
2026.01 | 0.72 | 0.0325 | |
2026.01 | 0.72 | 0.0368 | |
2026.01 | 0.75 | 0.036 | |
2026.01 | 0.79 | 0.0316 | |
2026.01 | 0.8 | 0.0373 | |
2026.01 | 0.8 | 0.0308 | |
2026.01 | 0.82 | 0.0301 | |
2026.01 | 0.82 | 0.0359 | |
2026.01 | 0.83 | 0.032 | |
2026.01 | 0.83 | 0.0358 | |
2026.01 | 0.85 | 0.033 | |
2026.01 | 0.85 | 0.0347 | |
2026.01 | 0.88 | 0.0393 | |
2026.01 | 0.88 | 0.0377 | |
2026.01 | 0.9 | 0.0365 | |
2026.01 | 0.9 | 0.0372 | |
2026.01 | 0.91 | 0.0379 | |
2026.01 | 0.93 | 0.038 | |
2026.01 | 0.93 | 0.0385 |