ResearchDatasetsWG-MFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCommonsense ReasoningWG-M76.45Accuracy18Common-sense reasoningWG-M (In-Distribution)83.61Accuracy12Commonsense ReasoningWG-M (test)83.23Accuracy10