ResearchTasksTurn-level correlation with human ratingsFor AI assistantsMarkdownContent indexTurn-level correlation with human ratingsFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMultiChallengeSKG-Eval0.74Spearman Correlation6May 19, 2026