Saved in:
Bibliographic Details
Main Author: Huang, Yichen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.03352
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912941228425216
author Huang, Yichen
author_facet Huang, Yichen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03352
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Perfect score on IPhO 2025 theory by Gemini agent
Huang, Yichen
Physics Education
Artificial Intelligence
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.
title Perfect score on IPhO 2025 theory by Gemini agent
topic Physics Education
Artificial Intelligence
url https://arxiv.org/abs/2603.03352