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

HEx-PHI and AdvBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Harmful Response GenerationHEx-PHI and AdvBench (test)
ASR96.86
7
Harmfulness EvaluationHEx-PHI & AdvBench Primary
Primary Average1.15
6
Showing 2 of 2 rows