ResearchDatasetsHard CorpusFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCode GenerationHard Corpus 192 problems 483.3Correctness (pass@1)12Code GenerationHard Corpus 4 (192 problems)75.5S-opt4