ResearchDatasetsARC-E, ARC-C, BoolQ, OBQA, HellaSwag, TruthfulQA, MMLUARC-E, ARC-C, BoolQ, OBQA, HellaSwag, TruthfulQA, MMLUFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsCommonsense Reasoning and Language ModelingARC-E, ARC-C, BoolQ, OBQA, HellaSwag, TruthfulQA, MMLU (test)92.4ARC-E Accuracy14
Commonsense Reasoning and Language ModelingARC-E, ARC-C, BoolQ, OBQA, HellaSwag, TruthfulQA, MMLU (test)92.4ARC-E Accuracy14