ResearchDatasetsAURATownFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsFactual Question AnsweringAURATown environment-grounded queries N=50, 3 seeds 1.076.6Factual Accuracy9Implicit-intent surfacingAURATown Scene A v2 (pilot)99.7Literal Score6
Factual Question AnsweringAURATown environment-grounded queries N=50, 3 seeds 1.076.6Factual Accuracy9