Perfect score on IPhO 2025 theory by Gemini agent
This work demonstrates a significant improvement in AI's ability to solve complex physics problems, potentially impacting AI development for scientific reasoning.
The paper describes a Gemini 3.1 Pro Preview agent that achieved a perfect score on the IPhO 2025 theory problems in five consecutive runs. This result surpasses previous AI model performances, which only reached gold medal levels.
The International Physics Olympiad (IPhO) is the world's most prestigious and renowned physics competition for pre-university students. IPhO problems require complex reasoning based on deep understanding of physical principles in a standard general physics curriculum. On IPhO 2025 theory problems, while gold medal performance by AI models was reported previously, it falls behind the best human contestant. Here we build a simple agent with Gemini 3.1 Pro Preview. We run it five times and it achieved a perfect score every time. However, data contamination could occur because Gemini 3.1 Pro Preview was released after the competition.