Self-Harm Classification on Human-Authored
13.69Bypass RateQwen3Guard-Gen-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3Guard-Gen-8BSafetyguard model=Qwen3Guard-Gen-8B2026.05 | 13.69 | |
| Llama-Guard-3-8BSafetyguard model=Llama-Guard-3-8B2026.05 | 29.61 | |
| Shieldgemma-9bSafetyguard model=Shieldgemma-9b2026.05 | 40.33 |