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

AegisSafety

Benchmarks

Task NameDataset NameSOTA ResultTrend
Prompt harmfulness detectionAegisSafety (test)
F1 Score99.5
41
Safety ClassificationAegisSafety V1 (test)
F1 Score92
14
Showing 2 of 2 rows