ResearchTasksMulti-task Language Understanding and ReasoningMulti-task Language Understanding and ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedOpenCompass SIQA, GSM8K, WiC, HumanEval, MMLU, CSQAWiSparse66.79SIQA30Feb 26, 2026