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

WGT

Benchmarks

Task NameDataset NameSOTA ResultTrend
Jailbreak Defense EvaluationWGT
Strong-Reject Score (SR)2.595
21
Jailbreak DetectionWGT
Accuracy90.17
13
Showing 2 of 2 rows