Modern generative models have demonstrated the ability to solve challenging mathematical problems. In many real-world settings, however, mathematical solutions must be expressed visually through diagrams, plots, geometric constructions, and structured symbolic layouts, where correctness depends on precise visual composition. This naturally raises the question of whether generative models can still do so when the answer must be rendered visually rather than written in text? To study this problem, we introduce MathGen, a rigorous benchmark of 900 problems spanning seven core domains, each paired with an executable verifier under a Script-as-a-Judge protocol for deterministic and objective evaluation. Experiments on representative open-source and proprietary text-to-image models show that mathematical fidelity remains a major bottleneck: even the best closed-source model reaches only 42.0% overall accuracy, while open-source models achieve just ~ 1-11%, often near 0% on structured tasks. Overall, current T2I models remain far from competent at even elementary mathematical visual generation.
@article{arxiv.2603.27959,
title = {MathGen: Revealing the Illusion of Mathematical Competence through Text-to-Image Generation},
author = {Ruiyao Liu and Hui Shen and Ping Zhang and Yunta Hsieh and Yifan Zhang and Jing Xu and Sicheng Chen and Junchen Li and Jiawei Lu and Jianing Ma and Jiaqi Mo and Qi Han and Zhen Zhang and Zhongwei Wan and Jing Xiong and Xin Wang and Ziyuan Liu and Hangrui Cao and Ngai Wong},
journal= {arXiv preprint arXiv:2603.27959},
year = {2026}
}