Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Perfect score on IPhO 2025 theory by Gemini agent

Yichen Huang

TL;DR

A simple agent is built with Gemini 3.1 Pro Preview to solve IPhO 2025 theory problems and it achieves a perfect score every time.

Abstract

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.

Perfect score on IPhO 2025 theory by Gemini agent

TL;DR

A simple agent is built with Gemini 3.1 Pro Preview to solve IPhO 2025 theory problems and it achieves a perfect score every time.

Abstract

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.
Paper Structure (17 sections, 6 equations, 1 figure, 1 table)

This paper contains 17 sections, 6 equations, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related work
  3. Dataset
  4. Data collection and pre-processing
  5. Curation
  6. Fig. 1(B) in Problem 1
  7. Fig. 3 in Problem 1
  8. Sub-problem B.3 in Problem 3
  9. Agent
  10. Agent for Problem 2
  11. Agent for Problems 1 and 3
  12. Discussions
  13. Evaluation
  14. Settings
  15. Grading
  16. ...and 2 more sections

Figures (1)

  • Figure 1: Left panel: Fig. 1(B) in Problem 1; Right panel: Fig. 2 in Problem 1.