About

Problem Hunting with LLMs

This website documents attempts by advanced Large Language Models (LLMs) to solve open mathematical problems. The idea for this project is due to mathematician Paata Ivanisvili.

Most of the current attempts are by GPT Pro 5.2.

Problem Sources

Erdos Problems

For Erdos problems, we track problems from two key resources:

MathOverflow Problems

MathOverflow problems are sourced from MathOverflow, a question and answer site for professional mathematicians. Each problem links to its original MathOverflow discussion.

Acknowledgments

Disclaimer

Important: LLM output is not fully reliable. The attempts documented on this website represent exploratory work by frontier AI models and should not be considered verified mathematical proofs.

While only the most advanced LLMs with a proven track record of making progress on open mathematical problems are featured here (such as GPT Pro, GPT 5.2, Gemini Deep Think, and Opus 4.5), their claimed solutions are not final and require rigorous verification by human mathematicians.

Any "solved" status indicated on this website means that the LLM produced output claiming to solve the problem - it does not mean the solution has been verified or accepted by the mathematical community.

Contributing

Contributions are welcome. Please see our Contributing Guidelines for details on how to submit new LLM attempts or improvements.

Only contributions featuring the most advanced frontier LLMs are accepted:

License

This project is licensed under the Apache License 2.0.

Links