List your company

Attack Success Rate Evaluation on HRL/LRL Safety Prompts English Text v1

1ASRClaude 3 Haiku
0.643.075.57.93Apr 13, 2025

Evaluation results

MethodLinks
Claude 3 Haiku2025.041
Claude 3.5 Sonnet2025.041
Gemini 1.5 Pro2025.042
Gemini 1.5 Flash2025.043
GPT-4o Mini2025.049
GPT-4o2025.0410