ResearchTasksCommonsense MCQCommonsense MCQFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMCSQAend-to-end72.08Accuracy9Jun 26, 2026Global-PIQAstandard cascade80.69Accuracy9Jun 26, 2026