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

GPTFuzzer

Benchmarks

Task NameDataset NameSOTA ResultTrend
LLM JailbreakingGPTFuzzer Scenario G3
Hypervolume0.696
21
LLM JailbreakingGPTFuzzer Scenario G2
Hypervolume77
21
LLM JailbreakingGPTFuzzer Scenario G1
Hypervolume0.708
21
Jailbreak DefenseGPTFuzzer
Harmful Score1
21
Showing 4 of 4 rows