Safety Moderation on Harmbench
86.4F1 Score
BingoGuard
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.12 | 86.4 | |
2025.12 | 86.2 | |
2025.12 | 85.7 | |
2025.12 | 84.9 | |
2025.12 | 84.8 | |
2025.12 | 83.5 | |
2025.12 | 78.6 |
BingoGuard
| Method | Links | |
|---|---|---|
2025.12 | 86.4 | |
2025.12 | 86.2 | |
2025.12 | 85.7 | |
2025.12 | 84.9 | |
2025.12 | 84.8 | |
2025.12 | 83.5 | |
2025.12 | 78.6 |