Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Jailbreak Safety Evaluation on English dataset Text

0.01StrongREJECT Rate

Claude 3 Haiku

0.00760.02380.040.0562Apr 13, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
0.01
0.01
0.02
0.02
2025.04
0.07
0.07