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

SafeguardBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Prompt ClassificationSEA-SafeguardBench
AUPRC (Average)93.6
29
Response ClassificationSEA-SafeguardBench
AUPRC89.7
9
Showing 2 of 2 rows