ResearchTasksReasoning and ClassificationReasoning and ClassificationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedBBH (Big-Bench Hard) (unseen)RLHFlow-Llama3.1-8B-D98.8BBH Temporal Sequences17Apr 10, 2026