ResearchTasksOut-of-Domain ReasoningOut-of-Domain ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedOut-of-Domain Reasoning Suite BGQA, CRUX Eval, Strategy QA, Table BenchQwQ-32B-Preview71.1BGQA Accuracy9May 20, 2026GPQAAFlow65.43Avg@8 Accuracy9Feb 26, 2026
Out-of-Domain Reasoning Suite BGQA, CRUX Eval, Strategy QA, Table BenchQwQ-32B-Preview71.1BGQA Accuracy9May 20, 2026