FormalProofBench: Can Models Write Graduate Level Math Proofs That Are Formally Verified?

Computer Science > Artificial Intelligence [Submitted on 27 Mar 2026] FormalProofBench: Can Models Write Graduate Level Math Proofs That Are Formally Verified? Nikil Ravi, Kexing Ying, Vasilii Nesterov, Rayan Krishnan, Elif Uskuplu, Bingyu Xia, Janitha Aswedige, Langston Nashold We present FormalProofBench, a private benchmark designed to evaluate whether AI models can produce formally verified mathematical proofs at the graduate level. Each task pairs a natural-language problem with a Lean~4 formal statement, and a model must output a Lean proof accepted by the Lean 4 checker. FormalProofBench targets advanced undergraduate and graduate mathematics, with problems drawn from qualifying exams and standard textbooks across topics including analysis, algebra, probability, and logic. We evaluate a range of frontier models with an agentic harness, and find that the best-performing foundation model achieves 33.5% accuracy, with performance dropping rapidly after that. In addition to the accuracy numbers, we also provide empirical analysis of tool-use, failure modes, cost and latency, thereby providing a thorough evaluation of the formal-theorem proving abilities of frontier models. Comments: Accepted at ICLR 2026 Workshop: VerifAI-2: The Second Workshop on AI Verification in the Wild. Live leaderboard hosted here: this https URL Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Programming Languages (cs.PL) Cite as: arXiv:2603.26996 [cs.AI]   (or arXiv:2603.26996v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.26996 Focus to learn more Submission history From: Nikil Ravi [view email] [v1] Fri, 27 Mar 2026 21:14:53 UTC (430 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.CL cs.LG cs.PL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)