ResearchTasksLLM-as-a-Judge RoutingFor AI assistantsMarkdownContent indexLLM-as-a-Judge RoutingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updated3 datasets Average (test)RACER90Accuracy12May 12, 2026