ResearchTasksGeneral Reasoning and GenerationGeneral Reasoning and GenerationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGSM8K, MATH500, HumanEval, MBPPVoidExpansion51.34Mean Accuracy5Jun 17, 2026