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

ARC-C, ARC-E, BoolQ, HellaSwag, PIQA, RTE, WinoGrande

Benchmarks

Task NameDataset NameSOTA ResultTrend
Zero-shot EvaluationARC-C, ARC-E, BoolQ, HellaSwag, PIQA, RTE, WinoGrande Zero-shot
Accuracy72.9
57
Showing 1 of 1 rows