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

Winogrande, HellaSwag, ARC, MMLU

Benchmarks

Task NameDataset NameSOTA ResultTrend
General Language UnderstandingWinogrande, HellaSwag, ARC, MMLU Consolidated
Average Accuracy71.09
11
Showing 1 of 1 rows