ResearchTasksGraduate-level Q&AGraduate-level Q&AFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGPQA 0-shotAR SFT27.5GPQA Accuracy (0-shot)9Apr 10, 2026GPQA diamond enTLPO33.87Accuracy5Apr 30, 2026