ResearchTasksLogical Reasoning Reliability EvaluationLogical Reasoning Reliability EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLGMT (Logic-Grounded Metamorphic Testing)Claude 4.5 Sonnet20.84MVR6May 26, 2026