ResearchTasksCompetitive Mathematical ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAMC 2023Qwen3-max100Pass@1 Accuracy37Jun 9, 2026AIME 2024DeepSeek-R1100Pass@1 Accuracy37Jun 9, 2026OlympiadBenchGemma-3-27b-it43.52Pass@502Feb 26, 2026