Towards a Large Physics Benchmark

TL;DR

This paper presents a comprehensive benchmark framework for evaluating large language models in fundamental physics, incorporating diverse question types and expert scoring to guide AI development in scientific research.

Contribution

It introduces a novel, community-driven physics benchmark with a multi-faceted scoring system and a living dataset to advance AI capabilities in physics understanding and problem solving.

Findings

Developed a diverse set of physics questions including conceptual, analytical, and open-ended types.

Implemented a scoring system based on correctness, difficulty, and surprise evaluated by experts.

Launched a living benchmark platform for continuous community contributions and updates.

Abstract

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.