List your company

Jailbreak Safety Evaluation on English dataset Text

0.01StrongREJECT RateClaude 3 Haiku
0.00760.02380.040.0562Apr 13, 2025

Evaluation results

MethodLinks
Claude 3 Haiku2025.040.01
Claude 3.5 Sonnet2025.040.01
Gemini 1.5 Flash2025.040.02
Gemini 1.5 Pro2025.040.02
GPT-4o2025.040.07
GPT-4o Mini2025.040.07