OpenAI publishes 722 manuscripts of maths results from an unreleased model

The GitHub repository groups them in 372 families; OpenAI says some results without Lean formalizations could have issues.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

Check our sources · 7 facts from 2 sources

On 6 October 2026 OpenAI published a broad range of new mathematical results from an internal frontier model, in a GitHub repository. The repository says its current catalogue holds 722 manuscripts organized into 372 families.

OpenAI says the model was posed approximately 4,000 problems and that, on average, each result used three hours of ChatGPT Pro thinking compute. The results are at different stages of verification: not all have Lean formalizations, and OpenAI says some of the unformalized results could have issues.

The model is unreleased; OpenAI says it is working to release it responsibly.

Your reaction

We count reactions per story and day, never who reacted. The counts help us choose what goes in the monthly issue. If you are signed in, your own page shows yours too.

Check our sources

Every sentence above is checked against these 2 sources.

1 Sharing AI progress in mathematicsOpenAI · 6 Oct 2026 · 3 facts

Open the source

OpenAI said on 6 October 2026 that it is releasing a broad range of new mathematical results produced by an internal frontier model. Quote: "We’re releasing a broad range of new mathematical results produced by an internal frontier model"

OpenAI October 6, 2026 Research Publication Sharing AI progress in mathematics View on GitHub (opens in a new window) Loading… Share We’re releasing a broad range of new mathematical results produced by an internal frontier model .
OpenAI says it is publishing the results in a GitHub repository and sharing Lean formalizations of many of the proofs. Quote: "we’re publishing the results in a GitHub repository"

For this release, we’re publishing the results in a GitHub repository, with protocols for paper revisions and citations.
OpenAI says it is working to responsibly release the model that produced these results. Quote: "are working to responsibly release the model that produced these results"

We want to directly empower scientists with state-of-the-art capabilities and are working to responsibly release the model that produced these results.

2 openai/math: READMEOpenAI (GitHub) · 4 facts

Open the source

OpenAI's repository says its current catalogue contains 722 manuscripts organized into 372 families. Quote: "The current catalogue contains 722 manuscripts organized into 372 families."

The current catalogue contains 722 manuscripts organized into 372 families.
The repository says the model was posed approximately 4,000 problems over the course of the evaluation. Quote: "the model was posed approximately 4,000 problems."

Over the course of the evaluation, the model was posed approximately 4,000 problems.
The repository says that on average each result used three hours of ChatGPT Pro thinking compute with the unreleased internal model. Quote: "On average, each result used three hours of ChatGPT Pro thinking compute with that model."

The vast majority of results were obtained with the same procedure using an unreleased internal OpenAI model. On average, each result used three hours of ChatGPT Pro thinking compute with that model.
The repository says not all results have Lean formalizations and that some of the unformalized results could have issues. Quote: "Some of the unformalized results could have issues."

have accompanying Lean formalizations. We will continue to update this repository with Lean formalizations as we obtain them. Some of the unformalized results could have issues.

Topics

The morning email

On the mornings we publish: the three top stories and up to four short ones. Free.

We email you a link to confirm. An issue may include one sponsor, always labelled Sponsored · Advertisement. Our emails count opens and clicks, not who made them. Unsubscribe in one click. What we keep