ResearchDatasetsLarge-scale tasksLarge-scale tasksFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsModel MergingLarge-scale tasks98.2Average Normalized Accuracy36Model MergingLarge-scale tasks 16 tasks merged91.5Average Normalized Accuracy12Model MergingLarge-scale tasks 12 tasks merged94.3Avg Normalized Acc12