ResearchTasksContextual ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedHellaSwagDeepSeek-V4-Pro Base88EM7Jun 19, 2026BigBenchHardSigma-MoE-Tiny Base63.23EM4Feb 26, 2026