ResearchDatasetsToolAlpacaToolAlpacaFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsTool UseToolAlpaca77.9Tool Use Success Rate26Tool-use InferenceToolAlpaca5.26Match Rate22Tool-use reasoningToolAlpaca66.73Accuracy20Tool selectionToolAlpaca97.42Accuracy20Tool usage simulationToolAlpaca evaluation78.38Procedure Score12