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

HellaSwag, PIQA, SIQA, WinoGrande

Benchmarks

Task NameDataset NameSOTA ResultTrend
Commonsense ReasoningHellaSwag (HS), PIQA, SIQA, WinoGrande (Wino)
HellaSwag Accuracy78.8
13
Showing 1 of 1 rows