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

NyayaBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Selective PredictionNyayaBench v2
Guaranteed Test Coverage (alpha=0.20)41.1
9
Intent ClassificationNyayaBench v2 (test)
Accuracy84.8
6
Showing 2 of 2 rows