ResearchTasksStep-level hallucination detectionStep-level hallucination detectionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedTruthfulQAStudent0.965AUROC6May 14, 2026PRM800KStudent99.8AUROC6May 14, 2026ProcessBenchTeacher91AUROC6May 14, 2026