ResearchTasksMeta-evaluation of Trajectory Evaluation MetricsMeta-evaluation of Trajectory Evaluation MetricsFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedSGRL Benchmarks AggregateInterval-Paired Preference (IPP)95.8Oracle Rank Accuracy (Acc)6Jun 17, 2026