FrontierMath Tier 4 (v1) - Private
Math · 2025-07-01
The Private split of FrontierMath Tier 4 (v1), the original 48-problem research-level private set Epoch AI evaluated before the v2 revision of 2026-06-12. Scores on v1 are not comparable with the v2 rows.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.5 Pro | 39.6 |
| GPT-5.4 Pro | 38.0 |
| GPT-5.5 | 35.4 |
| GPT-5.2 Pro | 31.3 |
| GPT-5.4 | 27.1 |
| Opus 4.7 | 22.9 |
| GPT-5.2 | 18.8 |
| Gemini 3.1 Pro Preview | 16.7 |