ResearchDatasetsDATE-LMDATE-LMFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsLanguage Model EvaluationDATE-LM MMLU, GSM8K, BBH62.07MMLU Accuracy7LLM fine-tuning data selectionDATE-LM MMLU, GSM8K, BBH official (test)61.87MMLU Accuracy3