ResearchTasksReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMultilingual MCQ Benchmarks Reasoning BucketDEPART0.088Sigma Alpha1May 28, 2026BBHQwen3-4B + FBS-Full (ours)41.5BBH Score1Feb 26, 2026BBH, ARC-Easy, ARC-Challenge, GSM8K——Primary metric0Apr 29, 2026General reasoning benchmarks——Primary metric0Apr 7, 2026Page 28 of 28PreviousNext