ResearchTasksComplex Reasoning and RetrievalFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedRetrieval-Heavy Tasks LMB, MMLU, GSM8K, SWDE, KV-RetLLAMA-3.2-1B60.1LMB Accuracy15Feb 26, 2026