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

Input Moderation Benchmark Suite

Benchmarks

Task NameDataset NameSOTA ResultTrend
Input ModerationInput Moderation Benchmark Suite (ToxicChat, OAIMod, Aegis, Aegis2, SSTest, HarmB, WildG)
Macro-average F188.2
22
Showing 1 of 1 rows