ResearchDatasetsGSM8K, MATH, HumanEval, MBPPFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGeneral Reasoning and GenerationGSM8K, MATH500, HumanEval, MBPP51.34Mean Accuracy5