ResearchDatasetsCommonsense ReasoningCommonsense ReasoningFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsCommonsense ReasoningCommonsense Reasoning Tasks HellaSwag, PIQA, WinoGrande33.9HellaSwag Accuracy4Commonsense ReasoningCommonsense Reasoning 170K SFT87.3Average Score3Question AnsweringCommonsense Reasoning25.4OBQA3PreviousPage 2 of 2Next