ResearchTasksRide-Hailing AdjudicationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedPassenger-CancelQwen3-VL-8B-Instruct95.7Normal Precision18Mar 19, 2026Driver-CancelQwen3-VL-8B-Instruct100Normal Precision18Mar 19, 2026AppealRideJudge-8B94.6Precision (Normal)18Mar 19, 2026Ride-Hailing Adjudication Overall 1.0 (test)RideJudge53.17Precision6Mar 19, 2026