ResearchTasksTruncated CoT AnsweringFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedFOLIOFaithfulness Only0.35AOC7Feb 26, 2026MuSRMAT-Steer33.6AOC7Feb 26, 2026ZebraLogicBench (ZLB)Faithfulness Only58.7AOC7Feb 26, 2026BBEHFaithfulness Only0.665AOC7Feb 26, 2026