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

Jailbreak Evaluation Dataset

Benchmarks

Task NameDataset NameSOTA ResultTrend
Offensive content generationJailbreak evaluation dataset Arabic
ASR65.8
4
Offensive content generationJailbreak Evaluation Dataset English
ASR76.7
4
Showing 2 of 2 rows