ResearchDatasetsDjangoFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCode GenerationDjango (test)83Accuracy28Semantic ParsingDJANGO3.4Generalization Error (G(W))10Code GenerationDjango75.4WS Prefix Match4Code GenerationDJANGO23.6Accuracy3Software EngineeringDjango 64K context 231 samples—Primary metric0