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

HellaSwag, WinoGrande, LAMBADA, PIQA, OpenBookQA, ARC

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringHellaSwag, WinoGrande, LAMBADA, PIQA, OpenBookQA, ARC-E, ARC-C
HellaSwag Accuracy79.2
28
Showing 1 of 1 rows