ResearchTasksRule-based ReasoningRule-based ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedRulearena NBAZero-shot (Default Imp.)67Accuracy3Jun 2, 2026Rulearena TaxStatic Workflow50Accuracy3Jun 2, 2026Rulearena AirlinesStatic Workflow98Accuracy3Jun 2, 2026