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

ARC, SIQA, PIQA, and WinoGrande

Benchmarks

Task NameDataset NameSOTA ResultTrend
Commonsense ReasoningARC-Easy, ARC-Challenge, SIQA, PIQA, and WinoGrande 0-shot
Reasoning Accuracy66.1
10
Showing 1 of 1 rows