ResearchTasksAggregate Benchmark PerformanceFor AI assistantsMarkdownContent indexAggregate Benchmark PerformanceFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedOverall Aggregate Math500, GSM8K, MMLU-s, GPQA, AIMEICT42.99Average P@115Jun 19, 2026