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

RTP

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-modal Toxicity AttackRTP (test)
Overall Score24.83
36
Safety DetectionRTP LX
Safety Score (De)98.76
8
Bias EvaluationRTP
Bias0.3
4
Showing 3 of 3 rows