Google DeepMind’s ‘AI co-mathematician’ sets FrontierMath Tier 4 record and helps resolve a Kourovka Notebook problem
Event confirmedAwaiting review
The takeaway
DeepMind’s agentic ‘AI co-mathematician’ on Gemini 3.1 Pro scored 48% (23/48) on FrontierMath Tier 4, versus 19% for Gemini 3.1 Pro alone and 39.6% for GPT-5.5 Pro.
Status
- Claim
Event confirmedAwaiting review
- Our reporting
- High confidence
- Verification
- Expert-checked
- Importance
- 3 of 5
- Last verified
- 19 October 2026
Your AI and this story
- GPT-6 Astra9 days after its cutoff
- Claude Opus 5.5In its training data
- Gemini 4 Hydrogen39 days after its cutoff
- Grok 4.7In its training data
It is after the cutoff of GPT-6 Astra and Gemini 4 Hydrogen, and can be in the training data of Claude Opus 5.5 and Grok 4.7.
Key facts
- arXiv 2605.06651
- FrontierMath Tier 4: 48% vs Gemini 3.1 Pro 19%, GPT-5.5 Pro 39.6%, Claude Opus 4.7 22.9%
- Earlier record: GPT-5.2 Pro 31% (15/48) in Jan 2026, per Epoch AI
- Semon Rezchikov: ‘I would rank, aesthetically, its general style of proofs as the best one of any models’
What happened
DeepMind wrapped Gemini in a team of generator, reviewer and literature agents designed to work alongside a mathematician.
Why it matters
FrontierMath Tier 4, built to resist AI for years, was nearly half solved 18 months after launch. The Lackenby collaboration showed the agent catching its own errors.
What is disputed or not yet verified
| Verification | Unrefereed preprint (arXiv 2605.06651); results checked by the collaborating mathematicians (e.g. Marc Lackenby), no independent check |
|---|
Sources
3 sources from 3 sites. Numbers match the chips in the text.
3 sources: 2 primary, 1 press
Primary
- AI co-mathematician (arXiv 2605.06651)arxiv.org, paper
- Epoch AI: new record on FrontierMath Tier 4 (Jan 2026)epochai.substack.com, official
Press
- The Rundown: Google DeepMind’s powerful AI co-mathematiciantherundown.ai, press
Changes
- Status confirmed → pending (unrefereed preprint; checks by collaborators only)
- Filed