guanning-ai/beyondaime

BeyondAIME是一个专门设计用于评估高级数学推理能力的测试集。它的创建遵循了一些核心原则，以确保公平且具有挑战性的评估。问题来源于高中和大学的数学竞赛，难度不低于AIME的第11-15题。每个问题都是独一无二的，以避免在标准预训练语料库中找到，从而真正测试模型的推理能力。该数据集专门测试推理能力，确保问题不要求超过标准大学水平的数学知识。问题设计避免了伪证明问题，并且每个问题的答案都是正整数，以便进行无歧义且100%准确的自动性能验证。

BeyondAIME is a curated test set designed to benchmark advanced mathematical reasoning. Its creation was guided by core principles to ensure a fair and challenging evaluation. Problems are sourced from high-school and university mathematics competitions, with a difficulty level greater than or equal to that of AIME Problems #11-15. Each problem is unique to avoid contamination in standard pre-training corpora and to truly test a models reasoning abilities. The dataset focuses on reasoning, ensuring problems do not require mathematical knowledge beyond the standard university level. The problems are designed to avoid pseudo-proof issues and each has a positive integer answer for unambiguous and 100% accurate automated verification of model performance.