ResearchDatasetsHumanEval, MBPPFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCodingHumanEval, MBPP50.2HumanEval Score35Code GenerationHumanEval+, MBPP+ v1.0 (test)88.41HumanEval+ Accuracy20