Skip to content

Competition maths (AIME-style problems)

Best independently measured score on Epoch AI's OTIS Mock AIME 2024–25 (45 problems), by model release date.

Topics: Mathematics, Benchmarks

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
DateLabelValue
14 Mar 2023GPT-4 (0314)0.6%
13 Jun 2023GPT-4 (0613)1.1%
11 Jul 2023Claude 2.02.5%
4 Mar 2024Claude 3 Opus4.7%
9 Apr 2024GPT-4 Turbo (Apr 2024)6.7%
23 Jul 2024Llama 3.1 405B9.7%
12 Sept 2024o1-mini (high)47%
17 Dec 2024o1 (high)73%
31 Jan 2025o3-mini (high)77%
16 Apr 2025o384%
7 Aug 2025GPT-5 (high)91%
11 Dec 2025GPT-5.2 (high)96%
5 Mar 2026GPT-5.498%
23 Apr 2026GPT-5.5 (xhigh)100%