Safety Moderation on Public Safety Benchmark Suite Average (EN)
86F1 ScoreWildguard
Evaluation Results
| Method | Links | |
|---|---|---|
| WildguardSize=7B2026.03 | 86 | |
| MD-JudgeSize=7B2026.03 | 85 | |
| FanarGuardSize=4B2026.03 | 83 | |
| Llama-Guard-3Size=8B2026.03 | 81 | |
| PolyGuard-MinistralSize=8B2026.03 | 79 | |
| PolyGuard-QwenSize=7B2026.03 | 78 | |
| PolyGuard-SmolSize=0.5B2026.03 | 73 | |
| ShieldGemma-2bSize=2B2026.03 | 68 |