OpenAI's experimental AI model has achieved gold medal-level performance at the 2025 International Mathematical Olympiad (IMO), solving five out of six problems and earning 35 out of 42 points. This marks a significant advancement in AI's ability to perform complex mathematical reasoning tasks.
The model was evaluated under the same conditions as human contestants, including two 4.5-hour sessions, no access to tools or the internet, and the requirement to provide detailed proofs for each problem. The AI's performance demonstrates progress in general-purpose reinforcement learning and test-time compute scaling, moving beyond narrow, task-specific methodologies.
OpenAI's CEO, Sam Altman, emphasized the broader implications of this achievement, stating, "This is an LLM doing math and not a specific formal math system; it is part of our main push towards general intelligence." The success of this model underscores the rapid advancements in AI and its potential applications in various fields requiring complex problem-solving skills.
While this achievement is notable, it is important to recognize that the results have not been independently verified by the IMO authorities. Further evaluations and validations are necessary to fully assess the model's capabilities and reliability in real-world applications.