ResearchDatasetsOverall AggregateOverall AggregateFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral PerformanceOverall Aggregate (test)72.4Average Score32General ReasoningOverall Aggregate46.7Average Accuracy15Aggregate Benchmark PerformanceOverall Aggregate Math500, GSM8K, MMLU-s, GPQA, AIME42.99Average P@115
Aggregate Benchmark PerformanceOverall Aggregate Math500, GSM8K, MMLU-s, GPQA, AIME42.99Average P@115