ResearchTasksMultiple-choice tasksMultiple-choice tasksFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedFrenchBenchTokens to Words82.2Accuracy61Mar 16, 2026FACTORTruthX65.83Accuracy (news)3Feb 26, 2026TriviaQATruthX66.79Accuracy3Feb 26, 2026Natural QuestionsTruthX59.6Accuracy3Feb 26, 2026