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

AdvBench-X

Benchmarks

Task NameDataset NameSOTA ResultTrend
Jailbreak Attack EvaluationAdvBench-X Swahili multilingual (test)
ASR (OpenAI Moderation)1.34
3
Jailbreak Attack EvaluationAdvBench-X Korean multilingual (test)
ASR (OpenAI Moderation)5.19
3
Showing 2 of 2 rows