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

SpeechJudge

Benchmarks

Task NameDataset NameSOTA ResultTrend
Preference EvaluationSpeechJudge
Acc@0.575
15
Pairwise preference predictionSpeechJudge human preference (test)
Accuracy70.4
4
Showing 2 of 2 rows