ResearchTasksMulti-domain reasoningMulti-domain reasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedBBHALRR87.39Accuracy39Jun 5, 2026AFlow-Stream (test)EVOCHAMBER98GSM8K Accuracy11May 13, 2026MMLU-ProSCVC88.7Math Accuracy10Mar 20, 2026