ResearchTasksMathematical reasoning, creative writing, and program synthesisMathematical reasoning, creative writing, and program synthesisFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCountdown, GSM8K, OlympiadBench, ROCStories, and MBPP (test)RandOpt K=5056.3Overall Score6Jun 1, 2026
Countdown, GSM8K, OlympiadBench, ROCStories, and MBPP (test)RandOpt K=5056.3Overall Score6Jun 1, 2026