List your company

Attack Success Rate Evaluation on HRL/LRL Safety Prompts English, Single Image v1

0ASRClaude 3.5 Sonnet
-0.02880.16560.360.5544Apr 13, 2025

Evaluation results

MethodLinks
Claude 3.5 Sonnet2025.040
GPT-4o Mini2025.040.03
Claude 3 Haiku2025.040.1
GPT-4o2025.040.13
Gemini 1.5 Pro2025.040.23
Gemini 1.5 Flash2025.040.72