Safety Moderation on Aegis, StrongReject, PolyGuard Aggregate 2.0
86.4Average F1 Score
YuFeng-XGuard
Updated 26d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 86.4 | 2.63 | |
2026.05 | 83.3 | 2.43 | |
2026.05 | 80.9 | 2.47 | |
2026.05 | 78.6 | 2.39 | |
2026.05 | 76.9 | 2.78 | |
2026.05 | 75.3 | 2.29 | |
2026.05 | 74.3 | 2.74 | |
2026.05 | 73.8 | 2.72 | |
2026.05 | 69.7 | 2.08 | |
2026.05 | 66.6 | 2.41 | |
2026.05 | 66.5 | 2.01 | |
2026.05 | 64.9 | 2.39 | |
2026.05 | 47.9 | 1.76 | |
2026.05 | 35.7 | 1.35 | |
2026.05 | 32.5 | 1.18 |