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

OCNLI

Benchmarks

Task NameDataset NameSOTA ResultTrend
Text ClassificationOCNLI (dev)
Max Accuracy79.4
20
Natural Language InferenceOCNLI
Accuracy68.15
17
ReasoningOCNLI
Score72.75
10
NLIOCNLI (test)
Accuracy0.8776
9
Sentence Pair ClassificationOCNLI (dev)
Accuracy79
9
Natural Language InferenceOCNLI 32 samples
Accuracy41.5
5
Showing 6 of 6 rows