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

Safety and Utility Evaluation on MaliciousGen & LMSYS-Chat

97.31Rule Score

Shadow-Level

82.708486.499290.2994.0808Jan 12, 2026
Updated 3mo ago

Evaluation Results

MethodLinks
2026.01
97.3196.35-0.925.06
2026.01
93.0892.12-1.055.16
2026.01
83.2773.27-1.715.01