IPhO 2025 Theory

The three-problem, 30-point theoretical examination of the 2025 International Physics Olympiad, used to test models against a fresh, human-graded physics exam.

Also known as: International Physics Olympiad 2025 Theoretical Examination, IPhO 2025 Theoretical Exam

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryreasoning
Subcategoryolympiad physics, theoretical examination
Page statusactive
Metricpercentage of maximum theory score
Directionhigher_is_better
Unit%
Dataset size3
PublisherInternational Physics Olympiad, 2025 edition, hosted by France (Palaiseau, École Polytechnique, near Paris)

What it measures

IPhO 2025 Theory evaluates whether a model can solve the same three multi-part theoretical physics problems that competed for medals at the 56th International Physics Olympiad, held in France in July 2025. Each problem requires deriving results algebraically from first principles and physical reasoning — not recalling a fact — under the same official mark scheme used for the roughly 400 human student contestants. It is single-turn, text-based (this repository did not confirm whether the official problem sheets also include diagrams), and testing is closer to multi-step quantitative reasoning than to closed-book knowledge recall, which is why this page treats it as a reasoning benchmark rather than a domain-knowledge one.

Task format

Three multi-part theoretical physics problems, each requiring worked derivations and numerical or symbolic answers; a model produces written solutions to be graded against the official IPhO 2025 marking scheme, the same instrument used for human contestants' scripts.

Models reporting this benchmark

These figures come from the model cards, which carry one collection date per card and no per-score attribution. They are shown as reported, not as verified evidence.
ModelProviderScoreCard as of
Muse SparkMeta82.62026-04

Data

This page as JSON · Edit on GitHub