arXiv:2508.02208v3 Announce Type: replace-cross
Abstract: Evaluating the mathematical capability of Large Language Models (LLMs) is a critical yet challenging frontier. Existing benchmarks fall short...
By Yebo Peng, Yaoming Li, Zixiang Liu, Zhizhuo Yang, Xinye Xu, Bowen Ye, Weijun Yuan, Zihan Wang, Tong Yang
arXiv:2606. 28747v1 Announce Type: new Abstract: Recent artificial intelligence (AI) systems have shown remarkable progress in mathematical reasoning.
By Kazuki Ota, Takayuki Osa, Tatsuya Harada
MathAdv is a diagnostic benchmark for formal theorem proving that covers 13 undergraduate- and graduate-level mathematics domains. It includes Lean 4 proofs and up to three auxiliary tasks—multiple-choice questions, fill-in-the-blank problems, and expert-crafted transformations—to probe knowledge, informal reasoning, and robustness to problem presentation. Evaluation of current theorem provers shows formalization is a major bottleneck, performance varies by domain, natural-language guidance can help or hinder models, and equivalent reformulations reveal significant robustness gaps.
By Jiaxin Yuan, Connor Martinez Lockhart, Xiaoyu Liu, Jiaqi Wang, Chenghao Deng, Xiayimei Han, Vlasios Mastrantonis, Dmitrii Gudin, Shaopeng Zhu, Abdirisak Abdullahi Mohamed, Bilal Hamdi Aytekin, Jiewen Lang, Zezheng Song, Furong Huang
The paper introduces HorizonMath, a benchmark of 113 largely unsolved mathematical problems across eight domains, paired with an open-source framework for automated verification. It focuses on the generator‑verifier gap, targeting problems that are hard to discover but easy to verify computationally, thereby avoiding costly formal proof verification or manual review. Using this framework, the authors found six novel solutions—three each from GPT‑5.4 Pro and GPT‑5.6 Sol—demonstrating that current models can contribute to mathematical research, while most state‑of‑the‑art models score below 10%.
By Erik Y. Wang, Sumeet R. Motwani, James V. Roggeveen, Eliot Hodges, Dulhan Jayalath, Charles London, Kalyan Ramakrishnan, Jakob Foerster, Cheng Zhang, Flaviu Cipcigan, Philip Torr, Alessandro Abate
LLMs have recently achieved strong results on formal proving benchmarks. However, existing evaluations remain heavily concentrated on competition-style problems and often fail to capture how models behave on longer, more dependency-rich mathematical developments.
Large language models (LLMs) have achieved remarkable performance on high-school and olympiad-style mathematics, yet their capabilities on advanced mathematics remain poorly understood. Existing benchmarks, however, fall short in both scope and evaluation granularity: they provide limited disciplinary coverage and often rely on final-answer correctness or coarse judgments, leaving the validity of the reasoning process inadequately assessed.