Safety Moderation on Beaver Response
84.4F1 ScoreWildGuard
Evaluation Results
| Method | Links | |
|---|---|---|
| WildGuardType=Response2025.12 | 84.4 | |
| GGuardType=Response2025.12 | 83 | |
| ShieldGemmaType=Response2025.12 | 77.1 | |
| Llama GuardType=Response2025.12 | 71.8 | |
| OAI ModeratorType=Response2025.12 | 65 |