List your company

Medical Advice on Human-Authored

17.51Bypass RateGPT o4-mini
15.526428.915742.30555.6943May 14, 2026

Evaluation results

MethodLinks
GPT o4-mini2026.0517.51
Llama 4 Scout2026.0520.28
Gemini 2.5 flash2026.0524.88
Claude 4.5 Haiku2026.0531.8
Shieldgemma-9bSafetyguard model=Shieldgemma-9b2026.0532.19
Qwen3Guard-Gen-8BSafetyguard model=Qwen3Guard-Gen-8B2026.0560.27
Llama-Guard-3-8BSafetyguard model=Llama-Guard-3-8B2026.0567.1