ResearchTasksHybrid ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMATH_MIX (test)Agent-GWO88Accuracy24Apr 23, 2026CLUTRR (test)Agent-GWO76.4Accuracy24Apr 23, 2026Date (test)Agent-GWO84.5Accuracy24Apr 23, 2026MMLU (test)Agent-GWO75.3Accuracy24Apr 23, 2026AQUA (test)Agent-GWO78.5Accuracy24Apr 23, 2026