ResearchTasksPairwise LLM EvaluationPairwise LLM EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedTravelDestQ-STRUM Debate74Win Rate Contrast2Feb 26, 2026HotelsQ-STRUM Debate82Win Rate (Contrast)2Feb 26, 2026RestaurantsQ-STRUM Debate83Win Rate (Contrast)2Feb 26, 2026