ResearchDatasetsT-EvalT-EvalFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsPlanningT-Eval official subset (test)92.2Precision14Agent Tool UseT-eval (Held-Out)71.8Accuracy14Tool EvaluationT-Eval67.6English Score13Tool UseT-Eval80.7Overall Score12