ResearchTasksLong-CoT ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMMLUSFI90.3Accuracy (Long-CoT MMLU)6Mar 13, 2026GPQASlow80.8Accuracy6Mar 13, 2026