ResearchDatasetsARC-C, BoolQ, HellaSwag, MMLU, OBQA, PIQA, RTE, WinograndeFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsZero-shot Evaluation AggregateARC-C, BoolQ, HellaSwag, MMLU, OBQA, PIQA, RTE, Winogrande Aggregate61.6Average Accuracy13
Zero-shot Evaluation AggregateARC-C, BoolQ, HellaSwag, MMLU, OBQA, PIQA, RTE, Winogrande Aggregate61.6Average Accuracy13