ResearchDatasetsMATH, GSM8K, SelfAware, and TruthfulQAMATH, GSM8K, SelfAware, and TruthfulQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsModel CalibrationMATH, GSM8K, SelfAware, and TruthfulQA combined0.086ECE10