ResearchTasksMacro-average ReasoningMacro-average ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedOverall NaturalPlan AIME 2024 GPQAPDP96.5Final Score (Macro-Avg)28Feb 26, 2026