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

FewGLUE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Recognizing Textual EntailmentFewGLUE RTE few-shot (32 examples) (dev)
Accuracy74
6
Recognizing Textual EntailmentFewGLUE RTE few-shot (32 examples) (test)
Accuracy70.5
4
Textual EntailmentFewGLUE CB (CommitmentBank) few-shot (32 examples) (test)
F1 Score79.9
4
Showing 3 of 3 rows