Saved in:
Bibliographic Details
Main Authors: Zhang, Yiming, Ma, Yingfan, Gu, Yanmei, Yang, Zhengkai, Zhuang, Yihong, Wang, Feng, Huang, Zenan, Wang, Yuanyuan, Huang, Chao, Song, Bowen, Lin, Cheng, Zhao, Junbo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.04766
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915376180232192
author Zhang, Yiming
Ma, Yingfan
Gu, Yanmei
Yang, Zhengkai
Zhuang, Yihong
Wang, Feng
Huang, Zenan
Wang, Yuanyuan
Huang, Chao
Song, Bowen
Lin, Cheng
Zhao, Junbo
author_facet Zhang, Yiming
Ma, Yingfan
Gu, Yanmei
Yang, Zhengkai
Zhuang, Yihong
Wang, Feng
Huang, Zenan
Wang, Yuanyuan
Huang, Chao
Song, Bowen
Lin, Cheng
Zhao, Junbo
contents Large Language Models (LLMs) have shown impressive performance in domains such as mathematics and programming, yet their capabilities in physics remain underexplored and poorly understood. Physics poses unique challenges that demand not only precise computation but also deep conceptual understanding and physical modeling skills. Existing benchmarks often fall short due to limited difficulty, multiple-choice formats, and static evaluation settings that fail to capture physical modeling ability. In this paper, we introduce ABench-Physics, a novel benchmark designed to rigorously evaluate LLMs' physical reasoning and generalization capabilities. ABench-Physics consists of two components: Phy_A, a static set of 400 graduate- or Olympiad-level problems; and Phy_B, a dynamic subset of 100 problems equipped with an automatic variation engine to test model robustness across changing conditions. All questions require precise numerical answers, with strict formatting and tolerance constraints. Our evaluation of several state-of-the-art LLMs reveals substantial performance gaps, highlighting persistent limitations in physical reasoning, especially in generalization to dynamic variants. ABench-Physics provides a challenging and diagnostic framework for advancing scientific reasoning in LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04766
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ABench-Physics: Benchmarking Physical Reasoning in LLMs via High-Difficulty and Dynamic Physics Problems
Zhang, Yiming
Ma, Yingfan
Gu, Yanmei
Yang, Zhengkai
Zhuang, Yihong
Wang, Feng
Huang, Zenan
Wang, Yuanyuan
Huang, Chao
Song, Bowen
Lin, Cheng
Zhao, Junbo
Machine Learning
Artificial Intelligence
Computation and Language
Large Language Models (LLMs) have shown impressive performance in domains such as mathematics and programming, yet their capabilities in physics remain underexplored and poorly understood. Physics poses unique challenges that demand not only precise computation but also deep conceptual understanding and physical modeling skills. Existing benchmarks often fall short due to limited difficulty, multiple-choice formats, and static evaluation settings that fail to capture physical modeling ability. In this paper, we introduce ABench-Physics, a novel benchmark designed to rigorously evaluate LLMs' physical reasoning and generalization capabilities. ABench-Physics consists of two components: Phy_A, a static set of 400 graduate- or Olympiad-level problems; and Phy_B, a dynamic subset of 100 problems equipped with an automatic variation engine to test model robustness across changing conditions. All questions require precise numerical answers, with strict formatting and tolerance constraints. Our evaluation of several state-of-the-art LLMs reveals substantial performance gaps, highlighting persistent limitations in physical reasoning, especially in generalization to dynamic variants. ABench-Physics provides a challenging and diagnostic framework for advancing scientific reasoning in LLMs.
title ABench-Physics: Benchmarking Physical Reasoning in LLMs via High-Difficulty and Dynamic Physics Problems
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2507.04766