ResearchTasksComplex Reasoning and RetrievalComplex Reasoning and RetrievalFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedRetrieval-Heavy Tasks LMB, MMLU, GSM8K, SWDE, KV-RetLLAMA-3.2-1B60.1LMB Accuracy15Feb 26, 2026