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

Content Safety Detection on WildGuardMix

95.9F1 Score

prompt–response verification framework

89.97291.51193.0594.589Jun 24, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
95.93.6
2026.06
90.2-