ResearchDatasetsPandasPlotBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsText-to-code generationPandasPlotBench9.7Code Error Rate8Text-to-VisualizationPandasPlotBench (test)79Code Exec Success3Multimodal code generationPandasPlotBench85.1Execution Rate2