AlphaGeometry solves olympiad geometry near gold-medallist level without human demonstrations
Result confirmed
The takeaway
AlphaGeometry (Nature, 17 Jan 2024) solved 25 of 30 IMO geometry problems from 2000–2022.
Status
- Claim
Result confirmed
- Our reporting
- High confidence
- Verification
- Peer-reviewed
- Importance
- 3 of 5
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6 AstraIn its training data
- Claude Opus 5.5In its training data
- Gemini 4 HydrogenIn its training data
- Grok 4.7In its training data
It happened before the cutoffs of all four assistants, so it can be in their training data.
Key facts
- IMO-AG-30 benchmark: 25/30 solved vs 10 for the previous state of the art (Wu’s method)
- Trained entirely on 100 million synthetic theorems and proofs, no human demonstrations
- A later paper showed Wu’s method plus a better deductive database rivals it (arXiv 2404.06405)
- AlphaGeometry 2 (2025) reached gold-medallist level on geometry
What happened
DeepMind generated synthetic geometry theorems at scale to train a language model that proposes auxiliary constructions, while a symbolic engine does the deduction.
Why it matters
It was a step towards the 2024 IMO silver and 2025 gold, and showed that synthetic data could replace scarce human proofs.
Sources
3 sources from 2 sites. Numbers match the chips in the text.
3 sources: 1 primary, 1 press, 1 reaction
Primary
- Solving olympiad geometry without human demonstrations (Nature)nature.com, paper
Press
- Nature news on AlphaGeometrynature.com, press
Reactions
- Wu’s method can boost symbolic AI to rival silver medalists (arXiv 2404.06405)arxiv.org, discussion
Changes
- Filed