Jailbreak Prompt Quality Evaluation on 500 randomly sampled prompts
81Similarity
PAIR
Updated 22d ago
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
2026.05 | 81 | 43.66 | - | 31 | - | 7 | 74 | 74 | |
2026.05 | 80 | 32.98 | 25 | 30 | 40 | 10 | 92 | 54 | |
2026.05 | 65 | 21.22 | 24 | 33 | 43 | 13 | 98 | 78 | |
2026.05 | 64 | 39.35 | - | - | 40 | 8 | 66 | 56 | |
2026.05 | 50 | 38.4 | 26 | 32 | 41 | 19 | 100 | 100 | |
2026.05 | 49 | 29.23 | 23 | 32 | - | 15 | 100 | 100 | |
2026.05 | 40 | 33.37 | 25 | 33 | 41 | 15 | 100 | 100 | |
2026.05 | 40 | 33.37 | 25 | 33 | 41 | 15 | 100 | 100 | |
2026.05 | 36 | 17.53 | 24 | 33 | 40 | 16 | 88 | 96 | |
2026.05 | 33 | 19.13 | 24 | 33 | 41 | 14 | 70 | 54 | |
2026.05 | 16 | 20.87 | 22 | - | - | - | 100 | 100 | |
2026.05 | 16 | 1,052.22 | 28 | 34 | 44 | 4 | 100 | 96 | |
2026.05 | 14 | 1,155.85 | - | - | 44 | 4 | 100 | 98 | |
2026.05 | 12 | 53.65 | - | - | - | 3 | 100 | 100 | |
2026.05 | 11 | 87.43 | - | - | - | 3 | 100 | 100 | |
2026.05 | 11 | 89.54 | - | - | - | 3 | 100 | 100 |