Competition maths (AIME-style problems)
Best independently measured score on Epoch AI's OTIS Mock AIME 2024–25 (45 problems), by model release date.
What this measures: Problems at the level of the American Invitational Mathematics Examination, the qualifier for the US Maths Olympiad team. In 2023 the best AI solved almost none.
0%50%100%202420252026
Saturated · last data Apr 2026: Top models score 100% (first GPT-5.5 and GPT-5.5 Pro, April 2026), so this test can no longer show progress and labs stopped reporting it. Now watch: FrontierMath and FrontierMath Erdős (open problems).
Each problem is worth about 2.2 points.
Sources: Epoch AI, MathArena (ETH Zurich)Data as of 9 Nov 2026
Show data table and sources
| Date | Label | Value |
|---|---|---|
| 14 Mar 2023 | GPT-4 (0314) | 0.6% |
| 13 Jun 2023 | GPT-4 (0613) | 1.1% |
| 11 Jul 2023 | Claude 2.0 | 2.5% |
| 4 Mar 2024 | Claude 3 Opus | 4.7% |
| 9 Apr 2024 | GPT-4 Turbo (Apr 2024) | 6.7% |
| 23 Jul 2024 | Llama 3.1 405B | 9.7% |
| 12 Sept 2024 | o1-mini (high) | 47% |
| 17 Dec 2024 | o1 (high) | 73% |
| 31 Jan 2025 | o3-mini (high) | 77% |
| 16 Apr 2025 | o3 | 84% |
| 7 Aug 2025 | GPT-5 (high) | 91% |
| 11 Dec 2025 | GPT-5.2 (high) | 96% |
| 5 Mar 2026 | GPT-5.4 | 98% |
| 23 Apr 2026 | GPT-5.5 (xhigh) | 100% |
- OTIS Mock AIME 2024–2025 (Epoch AI Benchmarking Hub) (Epoch AI)
- Epoch AI benchmark runs (CSV, CC BY 4.0) (Epoch AI)
- MathArena: AIME 2026 (MathArena (ETH Zurich))