ResearchTasksHonesty AlignmentHonesty AlignmentFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedNatural Questions (NQ) In-DomainEliCal85.16AUROC33Mar 5, 2026HHH alignmentAMBS86.1Win Rate (WR)20May 19, 2026HonestyBench OODCal-Only81.19Squad Score13Mar 5, 2026HonestyBench In-DomainEliCal85.16NQ Score13Mar 5, 2026OOD Aggregate AverageEliCal0.845AUROC3Mar 5, 2026In-Domain Aggregate AverageEliCal84.36AUROC3Mar 5, 2026