Safety Moderation on GuarEval Response
79.4F1 Score (Safety Moderation)GGuard
Evaluation Results
| Method | Links | |
|---|---|---|
| GGuardType=Response2025.12 | 79.4 | |
| ShieldGemmaType=Response2025.12 | 70.6 | |
| OAI ModeratorType=Response2025.12 | 57.1 | |
| Llama GuardType=Response2025.12 | 55.6 | |
| WildGuardType=Response2025.12 | 31.4 |