ResearchTasksCommonsense Reasoning and Language ModelingCommonsense Reasoning and Language ModelingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedARC-E, ARC-C, BoolQ, OBQA, HellaSwag, TruthfulQA, MMLU (test)REFT92.4ARC-E Accuracy14Jun 26, 2026