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

MMLU, GSM8K, HEval, IFEval, MTBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
General Language CapabilityMMLU, GSM8K, HEval, IFEval, MTBench
MMLU Accuracy76.4
16
Showing 1 of 1 rows