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

BEEP

Benchmarks

Task NameDataset NameSOTA ResultTrend
Offensive language detectionBEEP!
Precision90.66
5
Language DetoxificationBEEP (test)
Overall Offensiveness1.468
5
Toxic-neutral pair quality evaluationBEEP
Overall O Score2.3
1
Showing 3 of 3 rows