ResearchDatasetsKMMLU, CLIcK, KoBALT, MMLU, GPQAKMMLU, CLIcK, KoBALT, MMLU, GPQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsKnowledge EvaluationKMMLU, KMMLU Redux, KMMLU Pro, CLIcK, KoBALT, MMLU Pro, GPQA Diamond85.1Accuracy21
Knowledge EvaluationKMMLU, KMMLU Redux, KMMLU Pro, CLIcK, KoBALT, MMLU Pro, GPQA Diamond85.1Accuracy21