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

FalseReject

Benchmarks

Task NameDataset NameSOTA ResultTrend
Safety EvaluationFalseReject
USRBenign Rate79.2
18
Over-Refusal EvaluationFalseReject
ORR9.12
11
Showing 2 of 2 rows