ResearchDatasetsCommon Sense Reasoning and Knowledge SuiteFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMultiple Choice Question AnsweringCommon Sense Reasoning and Knowledge Suite (MMLU, BoolQ, PIQA, WiNoG, HSweg, ARC-E, ARC-C, OBQA) Mistral-7B base (val)62.5MMLU11
Multiple Choice Question AnsweringCommon Sense Reasoning and Knowledge Suite (MMLU, BoolQ, PIQA, WiNoG, HSweg, ARC-E, ARC-C, OBQA) Mistral-7B base (val)62.5MMLU11