ResearchTasksMathematical Proof ReasoningMathematical Proof ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedIMO-ProofBench Advanced (full set)Gemini 2.5 Pro58.6Mask-Proof Average@414Jun 16, 2026IMO-ProofBench-Advanced USAMO 2025 (5 problems)o390Mask-Proof Avg@47Jun 16, 2026IMO-ProofBench-Advanced Novel (22 problems)Gemini 2.5 Pro55.7Mask-Proof Avg@47Jun 16, 2026