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

Reasoning Tasks (PIQA, ARC-e, HS, WG)

Benchmarks

Task NameDataset NameSOTA ResultTrend
Zero-shot ReasoningReasoning Tasks (PIQA, ARC-e, HS, WG) Zero-shot
PIQA Accuracy80.41
18
Showing 1 of 1 rows