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

PIQA, WinoGrande, HellaSwag, BoolQ, SocialIQA, OpenBookQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Commonsense ReasoningPIQA, WinoGrande, HellaSwag, BoolQ, SocialIQA, OpenBookQA
PIQA Accuracy90.2
7
Showing 1 of 1 rows