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

ALERT

Benchmarks

Task NameDataset NameSOTA ResultTrend
Prohibited Content DetectionALERT
ASR15
34
Safety EvaluationALERT (test)
ASR0.2
7
Malicious Prompt DetectionBabelscape ALERT
Accuracy99.73
4
Showing 3 of 3 rows