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

RMB-SafeRLHF

Benchmarks

Task NameDataset NameSOTA ResultTrend
Judge AccuracyRMB-SafeRLHF (Target)
Accuracy69
4
Judge AccuracyRMB-SafeRLHF (Bench)
Accuracy85.6
4
Showing 2 of 2 rows