ResearchDatasetsQwen-Agent Code InterpreterQwen-Agent Code InterpreterFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsCode ExecutionQwen-Agent Code Interpreter Average70.5Accuracy3Code ExecutionQwen-Agent Code Interpreter Visualization-Easy68.4Accuracy3Code ExecutionQwen-Agent Code Interpreter Visualization-Hard72.6Accuracy3