ResearchTasksLanguage & ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCLUEWSCDeepSeek-V4-Pro Base85.2Exact Match (EM)3Jun 19, 2026WinoGrandeDeepSeek-V4-Pro Base81.5EM Score3Jun 19, 2026