ResearchDatasetsMacro-average (MMLU, MATH, GSM8K, BBH)Macro-average (MMLU, MATH, GSM8K, BBH)FollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsQuestion Answering and ReasoningMacro-average (MMLU, MATH, GSM8K, BBH) (test)—Cost Reduction0