ResearchTasksHuman Pairwise ComparisonFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedGaming Content N=60 samples (Unfamiliar Games)MeepleLM86.7Win %8Feb 26, 2026Gaming Content Familiar Games N=60 samplesMeepleLM83.3Win Rate8Feb 26, 2026