ResearchTasksReasoning Consistency EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMMLU-ProGPT-OSS52.9LAFF Score4May 29, 2026MT-ConsGPT-OSS85.7LAFF Score4May 29, 2026