Saved in:
Bibliographic Details
Main Authors: Barman, Kristian G., Caron, Sascha, Hasibi, Faegheh, Shalugin, Eugene, Marcet, Yoris, Otte, Johannes, de Regt, Henk W., Moody, Merijn
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.21695
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909710638120960
author Barman, Kristian G.
Caron, Sascha
Hasibi, Faegheh
Shalugin, Eugene
Marcet, Yoris
Otte, Johannes
de Regt, Henk W.
Moody, Merijn
author_facet Barman, Kristian G.
Caron, Sascha
Hasibi, Faegheh
Shalugin, Eugene
Marcet, Yoris
Otte, Johannes
de Regt, Henk W.
Moody, Merijn
contents We introduce a benchmark framework developed by and for the scientific community to evaluate, monitor and steer large language model development in fundamental physics. Building on philosophical concepts of scientific understanding and creativity, we develop a scoring system in which each question is scored by an expert for its correctness, difficulty, and surprise. The questions are of three forms: (i) multiple-choice questions for conceptual understanding, (ii) analytical problems requiring mathematical derivation, and (iii) openended tasks requiring complex problem solving. Our current dataset contains diverse set of examples, including a machine learning challenge to classify high-energy physics events, such as the four top quark signal. To ensure continued relevance, we propose a living benchmark, where physicists contribute questions, for instance alongside new publications. We invite contributions via: http://www.physicsbenchmarks.org/. We hope that this benchmark will enable a targeted AI development that can make a meaningful contribution to fundamental physics research.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21695
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards a Large Physics Benchmark
Barman, Kristian G.
Caron, Sascha
Hasibi, Faegheh
Shalugin, Eugene
Marcet, Yoris
Otte, Johannes
de Regt, Henk W.
Moody, Merijn
Data Analysis, Statistics and Probability
Artificial Intelligence
High Energy Physics - Phenomenology
Computational Physics
History and Philosophy of Physics
We introduce a benchmark framework developed by and for the scientific community to evaluate, monitor and steer large language model development in fundamental physics. Building on philosophical concepts of scientific understanding and creativity, we develop a scoring system in which each question is scored by an expert for its correctness, difficulty, and surprise. The questions are of three forms: (i) multiple-choice questions for conceptual understanding, (ii) analytical problems requiring mathematical derivation, and (iii) openended tasks requiring complex problem solving. Our current dataset contains diverse set of examples, including a machine learning challenge to classify high-energy physics events, such as the four top quark signal. To ensure continued relevance, we propose a living benchmark, where physicists contribute questions, for instance alongside new publications. We invite contributions via: http://www.physicsbenchmarks.org/. We hope that this benchmark will enable a targeted AI development that can make a meaningful contribution to fundamental physics research.
title Towards a Large Physics Benchmark
topic Data Analysis, Statistics and Probability
Artificial Intelligence
High Energy Physics - Phenomenology
Computational Physics
History and Philosophy of Physics
url https://arxiv.org/abs/2507.21695