ResearchDatasets3 datasetsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsTime series forecasting3 datasets averaged (test)0.08MAE22Selective Prediction3 datasets (mean over all 21 runs)0.79AUROC16LLM-as-a-Judge Routing3 datasets Average (test)90Accuracy12Selective Prediction3 datasets (Trace)0.798AUROC8