ResearchDatasetsToolUseFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsTool UseToolUse69.2Task Accuracy18Cross-task generalizationToolUse53.6Test Final Score3Function CallingToolUse (test)91.2Structural Accuracy3