List your company

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

0Attack Success RateGemini 1.5 Flash
-0.965.521218.48Apr 13, 2025

Evaluation results

MethodLinks
Gemini 1.5 Flash2025.040
Gemini 1.5 Pro2025.040
Claude 3.5 Sonnet2025.042
Claude 3 Haiku2025.046
GPT-4o Mini2025.0418
GPT-4o2025.0424