ResearchDatasetsMACEFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsConfidence CalibrationMACE (test)81.2AUROC84Model CalibrationMACE82.4AUROC84LLM CalibrationMACE8.6ECE60MACE PredictionMACE Prediction n=350 (test)81.8AUROC1