ResearchTasksLong-CoT ReasoningLong-CoT ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMMLUSFI90.3Accuracy (Long-CoT MMLU)6Mar 13, 2026GPQASlow80.8Accuracy6Mar 13, 2026