ResearchTasksQuery routing and tool-calling accuracy evaluationFor AI assistantsMarkdownContent indexQuery routing and tool-calling accuracy evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedHeld-out 12,282 examples (test)Oracle89.39Accuracy15May 11, 2026