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

ARC-C, MMLU, TruthfulQA, Winogrande, HellaSwag, PIQA, MathQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Few-shot Language UnderstandingARC-C, MMLU, TruthfulQA, Winogrande, HellaSwag, PIQA, MathQA Few-shot
ARC-C Score26.79
6
Showing 1 of 1 rows