ResearchTasksPairwise Reasoning Quality EvaluationPairwise Reasoning Quality EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedZillowNexus85.8Domain Relevance (Win %)2May 15, 2026StocksNexus51.4Domain Relevance (Nexus Win)2May 15, 2026