Response Harmfulness Detection on HarmBench Suite (HarmBench, SafeRLHF, BeaverTails, XSTest, WildGuard)
0.8333Macro Avg F1
COLAGUARD
Updated 5d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.05 | 0.8333 | - | - | - | 0.8155 | |
2026.05 | 0.8313 | - | - | - | 0.8122 | |
2026.05 | 0.8256 | - | - | - | 0.8022 | |
2026.05 | 0.8249 | - | - | - | 0.808 | |
2026.05 | 0.81 | - | - | - | 0.7795 | |
2026.05 | 0.8078 | - | - | - | 0.7906 | |
2026.05 | 0.8004 | - | - | - | 0.7867 | |
2026.05 | 0.7434 | - | - | - | 0.7445 | |
2026.05 | 0.7348 | - | - | - | 0.766 | |
2026.05 | 0.717 | - | - | - | 0.6699 | |
2026.05 | 0.7115 | - | - | - | 0.6497 | |
2026.05 | 0.6954 | - | - | - | 0.6922 | |
2026.05 | 0.6934 | - | - | - | 0.667 | |
2026.05 | 0.6632 | - | - | - | 0.6549 | |
2026.05 | 0.6588 | - | - | - | 0.6941 | |
2026.05 | 0.6146 | - | - | - | 0.6355 | |
2026.05 | 0.6 | - | - | - | 0.5827 | |
2026.05 | 0.5962 | - | - | - | 0.6279 | |
2026.05 | 0.576 | - | - | - | 0.5567 | |
2026.05 | 0.5464 | - | - | - | 0.5773 | |
2026.05 | 0.3379 | - | - | - | 0.2724 | |
2026.05 | - | 3,801.03 | 281.96 | 0.2122 | - | |
2026.05 | - | 318.9 | 13 | 2.5041 | - | |
2026.05 | - | 4,407.8 | 289.4 | 0.1838 | - | |
2026.05 | - | 342 | 12.9 | 2.3601 | - |