Prompt Harmfulness Classification on Public Prompt Harmfulness Benchmarks Suite
73ToxiC Score
Aegis-Guard-P
Updated 4d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2024.06 | 73 | 74.7 | 82.9 | 99 | 70.5 | 80 | |
2024.06 | 70.8 | 72.1 | 89.4 | 99.5 | 98.9 | 86.1 | |
2024.06 | 70 | 67.5 | 84.8 | 100 | 77.7 | 80 | |
2024.06 | 68.3 | 70.5 | 84.4 | 100 | 100 | 84.6 | |
2024.06 | 61.6 | 75.8 | 74.1 | 93 | 67.2 | 74.4 | |
2024.06 | 47.1 | 76.1 | 71.8 | 95.8 | 94 | 77 | |
2024.06 | 25.4 | 79 | 31.9 | 63 | 9.6 | 41.8 |