FrontierMath Tier 4
Hard research mathematics
v2mathactive
Definition
- Version
- v2
- Category
- math
- Maintainer
- not in the notes
- Status
- active
- Home page
- not in the notes
Sources
- OpenAI Launches GPT-6 Astra, Pricing, Benchmarks and Who Gets It First pasqualepillitteri.it https://pasqualepillitteri.it/en/news/14246/openai-launches-gpt-6-astra-pricing-benchmarks
Scores
| Model | Score | Who ran it | Setting | View or population | Date | Source |
|---|---|---|---|---|---|---|
 GPT-6 Astra | 97.6 % | vendor-reported | – | – | – | pasqualepillitteri.it |
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "FrontierMath Tier 4", https://aurion.semai.id/benchmarks/frontiermath-tier-4-v2/, records of October 2026.