ResearchTasksRational Ordering EvaluationRational Ordering EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedOR-BIAS-BENCH OOD 200 samplesclaude-haiku-4.50.036Bias7Feb 26, 2026OR-BIAS-BENCH 400 samples (In-Distribution)claude-haiku-4.50Bias7Feb 26, 2026