ResearchDatasetsGTMGTMFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsTool Use EvaluationGTM89.4Average Score11Tool Error DetectionGTM Error Detection95.3Detection Rate11Tool Response GenerationGTM Multi-turn97.2Format Score11Tool Response GenerationGTM Single-turn99.6Format Score11