ResearchTasksMathematical ProofFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedUSAMO 2026STAR-PólyaMath99.4Overall Score (%)9May 20, 2026IMO-ProofBench Basic, Advanced, OverallAletheia91.9Advanced Score9Mar 20, 2026IMO 2025STAR-PólyaMath88.69Score8May 20, 2026