ResearchDatasetsToDsToDsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsTime-Series Anomaly DetectionTODS94.25F1 Score24End-to-End Dialogue ModelingToDs (test)95.45Intent Accuracy11Intent ClassificationToDs benchmark GPT-2 backbone (test)0.875Accuracy11Anomaly DetectionTODS univariate65.2VUS-PR8