ResearchTasksBehavioral Similarity AnalysisFor AI assistantsMarkdownContent indexBehavioral Similarity AnalysisFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedτ-Bench and τ2-Bench (test)Sonnet 4.582.6GED Score18Apr 24, 2026