ResearchDatasetsCountdown, GSM8K, OlympiadBench, ROCStories, and MBPPCountdown, GSM8K, OlympiadBench, ROCStories, and MBPPFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical reasoning, creative writing, and program synthesisCountdown, GSM8K, OlympiadBench, ROCStories, and MBPP (test)56.3Overall Score6
Mathematical reasoning, creative writing, and program synthesisCountdown, GSM8K, OlympiadBench, ROCStories, and MBPP (test)56.3Overall Score6