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

esnli

Benchmarks

Task NameDataset NameSOTA ResultTrend
Binary ClassificationESNLI
Accuracy99
18
Text to AudioESNLI (test)
Accuracy79.6
6
Text to TextESNLI (test)
Accuracy (ESNLI Test)80.6
6
Audio to AudioESNLI (test)
Accuracy77.1
6
Audio to TextESNLI (test)
Accuracy77.4
6
Explanation GenerationeSNLI complete (test)
BERTScore88.84
6
Generative Taskesnli
BS Score60.02
4
Reasoning trace quality evaluationeSNLI
Grammar Score5.9
2
Showing 8 of 8 rows