ResearchDatasetsMMLU, ARC-C, PIQA, WinoG, GSM8K, HellaSwag, GPQA, RACEFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsZero-shot language evaluationMMLU, ARC-C, PIQA, WinoG, GSM8K, HellaSwag, GPQA, RACE zero-shot60.94Average Score9
Zero-shot language evaluationMMLU, ARC-C, PIQA, WinoG, GSM8K, HellaSwag, GPQA, RACE zero-shot60.94Average Score9