ResearchTasksAdding MistakeFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedFOLIOFaithfulness Only0.714AOC7Feb 26, 2026MuSRFaithfulness Only0.731AOC7Feb 26, 2026ZebraLogicBench (ZLB)Faithfulness Only83.8AOC7Feb 26, 2026BBEHFaithfulness Only67.2AOC7Feb 26, 2026