{"slug": "frontiermath-erd-h-o-s", "title": "FrontierMath Erd\\H{o}s", "summary": "A new benchmark called FrontierMath Erdős (FME), introduced in a paper submitted to arXiv on 6 September 2026, evaluates AI systems on 68 Erdős problems that remained open as of August 2026, requiring them to prove or disprove each conjecture in the Lean proof assistant. The 68 problems were selected by the paper's second author from 652 open problems on erdosproblems.com, and five AI models were tested autonomously under a budget of $300 per problem. GPT-6 Astra scored 3%, the only model to resolve any problem, while all other models scored 0%.", "body_md": "# Computer Science > Computation and Language\n\n  [Submitted on 6 Sep 2026]\n\n# Title:FrontierMath Erdős\n\n[View PDF](https://arxiv.org/pdf/2609.25050)\n\n[HTML (experimental)](https://arxiv.org/html/2609.25050v1)\n\nAbstract:We introduce FrontierMath Erdős (FME), a benchmark of 68 Erdős problems that are open as of August 2026. To solve a task in FME, AI systems must resolve (prove or disprove) one of the 68 conjectures in the proof assistant Lean. Our 68 problems were selected by the second author among 652 open problems on [this http URL](http://erdosproblems.com) for their mathematical interest and difficulty. AIs have recently resolved several open problems in mathematics, but these demonstrations fall short of a systematic study of AI capabilities. FME evaluates every AI model on the same fixed problems, autonomously and under the same budget. We evaluated five AIs with a budget of \\$300 per problem. One (GPT-6 Astra) scored 3%, and all others scored 0%.\n    \n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/frontiermath-erd-h-o-s", "canonical_source": "https://arxiv.org/abs/2609.25050", "published_at": "2026-09-23 04:00:00+00:00", "updated_at": "2026-09-23 04:25:31.885990+00:00", "lang": "en", "topics": ["ai-research", "large-language-models", "artificial-intelligence", "machine-learning"], "entities": ["FrontierMath Erdős", "Lean", "GPT-6 Astra", "arXiv", "erdosproblems.com"], "alternates": {"html": "https://wpnews.pro/news/frontiermath-erd-h-o-s", "markdown": "https://wpnews.pro/news/frontiermath-erd-h-o-s.md", "text": "https://wpnews.pro/news/frontiermath-erd-h-o-s.txt", "jsonld": "https://wpnews.pro/news/frontiermath-erd-h-o-s.jsonld"}}