ResearchDatasetsIn-domain Step-level BenchmarkIn-domain Step-level BenchmarkFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsFaithfulness detectionIn-domain Step-level Benchmark Agent80.2FF110Faithfulness detectionIn-domain Step-level Benchmark Knowledge83.4FF110Faithfulness detectionIn-domain Step-level Benchmark Reasoning84.5FF110