ResearchTasksMulti-domain reasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedBBHALRR87.39Accuracy39Jun 5, 2026AFlow-Stream (test)EVOCHAMBER98GSM8K Accuracy11May 13, 2026MMLU-ProSCVC88.7Math Accuracy10Mar 20, 2026