ResearchDatasetsMMLU, BoolQ, ARC-e, PIQA, Hellaswag, OBQA, WinograndeMMLU, BoolQ, ARC-e, PIQA, Hellaswag, OBQA, WinograndeFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsLanguage Understanding and ReasoningMMLU, BoolQ, ARC-e, PIQA, Hellaswag, OBQA, Winogrande (test)28.69MMLU10
Language Understanding and ReasoningMMLU, BoolQ, ARC-e, PIQA, Hellaswag, OBQA, Winogrande (test)28.69MMLU10