FrontierMath-Tier-4-2025-07-01-Private
FrontierMath Tier 4 (Jul 2025) — the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
39
Models Tested
37.5
Top Score
7.6
Average Score
Rankings
| # | Model | Score | Bar |
|---|---|---|---|
| 1 | 37.5 | ||
| 2 | 27.1 | ||
| 3 | 22.9 | ||
| 4 | 18.8 | ||
| 5 | 18.8 | ||
| 6 | 18.8 | ||
| 7 | 16.7 | ||
| 8 | 14.6 | ||
| 9 | 12.5 | ||
| 10 | 12.5 | ||
| 11 | 12.5 | ||
| 12 | 12.5 | ||
| 13 | 8.3 | ||
| 14 | 6.3 | ||
| 15 | 6.3 | ||
| 16 | M Kimi K2.5moonshotai | 4.2 | |
| 17 | 4.2 | ||
| 18 | 4.2 | ||
| 19 | 4.2 | ||
| 20 | 4.2 | ||
| 21 | 4.2 | ||
| 22 | 4.2 | ||
| 23 | 4.2 | ||
| 24 | ZA GLM 4.6z-ai | 2.1 | |
| 25 | ZA GLM 5 Turboz-ai | 2.1 | |
| 26 | ZA GLM 5z-ai | 2.1 | |
| 27 | 2.1 | ||
| 28 | 2.1 | ||
| 29 | 2.1 | ||
| 30 | 2.1 | ||
| 31 | 2.1 | ||
| 32 | ZA GLM 4.7z-ai | 0.1 | |
| 33 | M Kimi K2 Thinkingmoonshotai | 0.1 | |
| 34 | 0.1 | ||
| 35 | 0.1 | ||
| 36 | 0.1 | ||
| 37 | 0.1 | ||
| 38 | 0.1 | ||
| 39 | 0.1 |