OpenAI's new internal model outperforms GPT-6 Astra in math

Skip to content

Alex Getman @alexgetmancom · 8 Sep 2026, 19:00 UTC · Updated 31 Oct 2026, 20:59 UTC

Tests & comparisons

OpenAI has a new internal model that is way ahead of GPT 6 Astra in math

On a curated set of open math problems, it reaches about 48% pass rate with more test time compute.

GPT 6 Astra peaks at around 17%.

Chart showing OpenAI's internal model reaches ~48% pass rate on math problems with more compute, while GPT-6 Astra peaks at ~17%.

OpenAI AI and mathematics

Русская версия Markdown

Related posts

8 Sep🚨 OpenAI’s new internal model solved the Navier-Stokes Millennium Prize Problem Around 10,000 agents worked on the solution for 88 hours, powered by a model significantly more capable than GPT 6 Astra. After the solution was found, GPT 6 Astra formalized and verified the proof…

OpenAI AI and mathematics

8 SepAI may have just cracked one of the hardest open problems in mathematics: Navier–Stokes. And the story behind it is getting more interesting. Tristan Buckmaster says OpenAI told him its internal research model had generated a roughly 100-page proof. The proof has not been made…

Claude OpenAI AI and mathematics AI security

20 JulFable disproved an 87-year-old conjecture Mathematicians Levent Alpöge and Akhil Mathew asked the model to find a counterexample to the Jacobian Conjecture from 1939. Claude Fable 5 came back with a short formula. And it actually works. In plain English, the conjecture said…

Claude Fable 5 Anthropic Claude AI and mathematics

13 NovGPT Dots is starting to roll out across the EU. For those unfamiliar, Dots is OpenAI’s proactive assistant, similar to Grok’s bot or a locally running Hermes agent. It can work on its own cloud computer or control your machines via Codex, orchestrating tasks across them.