ResearchDatasetsOOL-PairsOOL-PairsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsLong-context reasoningOOL-Pairs5.1Latency (s)27Long-context reasoning (Pairs)OOL-Pairs64.3Accuracy27