UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models

TL;DR

UGPhysics is a large, comprehensive benchmark designed to evaluate undergraduate-level physics reasoning in LLMs, highlighting current models' limitations and guiding future improvements.

Contribution

The paper introduces UGPhysics, a detailed benchmark with 5,520 physics problems in multiple languages and a novel evaluation pipeline, filling a critical gap in physics reasoning assessment for LLMs.

Findings

Highest accuracy achieved is 49.8% by OpenAI-o1-mini.

Current LLMs show significant room for improvement in physics reasoning.

UGPhysics covers diverse subjects and reasoning skills, providing a robust evaluation framework.

Abstract

Large language models (LLMs) have demonstrated remarkable capabilities in solving complex reasoning tasks, particularly in mathematics. However, the domain of physics reasoning presents unique challenges that have received significantly less attention. Existing benchmarks often fall short in evaluating LLMs' abilities on the breadth and depth of undergraduate-level physics, underscoring the need for a comprehensive evaluation. To fill this gap, we introduce UGPhysics, a large-scale and comprehensive benchmark specifically designed to evaluate UnderGraduate-level Physics (UGPhysics) reasoning with LLMs. UGPhysics includes 5,520 undergraduate-level physics problems in both English and Chinese, covering 13 subjects with seven different answer types and four distinct physics reasoning skills, all rigorously screened for data leakage. Additionally, we develop a Model-Assistant Rule-based Judgment (MARJ) pipeline specifically tailored for assessing answer correctness of physics problems, ensuring accurate evaluation. Our evaluation of 31 leading LLMs shows that the highest overall accuracy, 49.8% (achieved by OpenAI-o1-mini), emphasizes the necessity for models with stronger physics reasoning skills, beyond math abilities. We hope UGPhysics, along with MARJ, will drive future advancements in AI for physics reasoning. Codes and data are available at https://github.com/YangLabHKUST/UGPhysics .