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

MM-Safety

Benchmarks

Task NameDataset NameSOTA ResultTrend
Safety EvaluationMM-Safety
ASR0.4
57
Safety and Helpfulness EvaluationMM-Safety
Safety Score88.71
18
Jailbreak attacksMM-Safety
Safety Rate99.9
12
Safety AlignmentMM-Safety
ASR2.2
8
Showing 4 of 4 rows