List your company

Attack Success Rate Evaluation on HRL/LRL Safety Prompts Welsh Multi-Image v1

0ASRClaude 3 Haiku
-0.00240.01380.030.0462Apr 13, 2025

Evaluation results

MethodLinks
Claude 3 Haiku2025.040
GPT-4o Mini2025.040
Gemini 1.5 Flash2025.040.02
Gemini 1.5 Pro2025.040.02
Claude 3.5 Sonnet2025.040.04
GPT-4o2025.040.06