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

IH-Challenge

Benchmarks

Task NameDataset NameSOTA ResultTrend
Online Learning of Adversarial RobustnessIH-Challenge (composite category)
Final Score75.2
5
Overrefusal evaluationIH-Challenge overrefusal
Performance Score1
2
Showing 2 of 2 rows