PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning

• URL: http://arxiv.org/abs/2502.12054v1
• Date: Mon, 17 Feb 2025 17:24:14 GMT
• Title: PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning
• Authors: Xinyu Zhang, Yuxuan Dong, Yanrui Wu, Jiaxing Huang, Chengyou Jia, Basura Fernando, Mike Zheng Shou, Lingling Zhang, Jun Liu,
• Abstract summary: We present PhysReason, a 1,200-problem benchmark for evaluating large language models. Problems require an average of 8.1 solution steps, with hard requiring 15.6. Top-performing models like Deepseek-R1, Gemini-2.0-Flash-Thinking, and o3-mini-high achieve less than 60% on answer-level evaluation.
• Score: 36.193595420239845
• License:
• Abstract: Large language models demonstrate remarkable capabilities across various domains, especially mathematics and logic reasoning. However, current evaluations overlook physics-based reasoning - a complex task requiring physics theorems and constraints. We present PhysReason, a 1,200-problem benchmark comprising knowledge-based (25%) and reasoning-based (75%) problems, where the latter are divided into three difficulty levels (easy, medium, hard). Notably, problems require an average of 8.1 solution steps, with hard requiring 15.6, reflecting the complexity of physics-based reasoning. We propose the Physics Solution Auto Scoring Framework, incorporating efficient answer-level and comprehensive step-level evaluations. Top-performing models like Deepseek-R1, Gemini-2.0-Flash-Thinking, and o3-mini-high achieve less than 60% on answer-level evaluation, with performance dropping from knowledge questions (75.11%) to hard problems (31.95%). Through step-level evaluation, we identified four key bottlenecks: Physics Theorem Application, Physics Process Understanding, Calculation, and Physics Condition Analysis. These findings position PhysReason as a novel and comprehensive benchmark for evaluating physics-based reasoning capabilities in large language models. Our code and data will be published at https:/dxzxy12138.github.io/PhysReason.

Related papers

• MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations [90.07275414500154]
  We observe significant performance drops on MATH-P-Hard across various models. We also raise concerns about a novel form of memorization where models blindly apply learned problem-solving skills.
  arXiv  Detail & Related papers  (2025-02-10T13:31:46Z)
• UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models [39.917074900737575]
  Large language models (LLMs) have demonstrated remarkable capabilities in solving complex reasoning tasks. 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.
  arXiv  Detail & Related papers  (2025-02-01T06:42:02Z)
• Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models [41.88825441287559]
  Existing large language models (LLMs) frequently fail due to a lack of knowledge or incorrect knowledge application. We propose Physics Reasoner, a knowledge-augmented framework to solve physics problems with LLMs. Given a physics problem, Physics Reasoner solves it through three stages: problem analysis, formula retrieval, and guided reasoning. Empirically, Physics Reasoner mitigates the issues of insufficient knowledge and incorrect application, achieving state-of-the-art performance on SciBench with an average accuracy improvement of 5.8%.
  arXiv  Detail & Related papers  (2024-12-18T12:33:50Z)
• Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models [63.31878920079154]
  We propose a benchmark specifically designed to assess large language models' mathematical reasoning at the Olympiad level. Unlike existing Olympiad-related benchmarks, our dataset focuses exclusively on mathematics and comprises a vast collection of 4428 competition-level problems with rigorous human annotation. Our experimental results show that even the most advanced models, OpenAI o1-mini and OpenAI o1-preview, struggle with highly challenging Olympiad-level problems, with 60.54% and 52.55% accuracy, highlighting significant challenges in Olympiad-level mathematical reasoning.
  arXiv  Detail & Related papers  (2024-10-10T14:39:33Z)
• OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems [62.06169250463104]
  We present OlympiadBench, an Olympiad-level bilingual multimodal scientific benchmark, featuring 8,476 problems from Olympiad-level mathematics and physics competitions. The best-performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics. Our analysis orienting GPT-4V points out prevalent issues with hallucinations, knowledge omissions, and logical fallacies.
  arXiv  Detail & Related papers  (2024-02-21T18:49:26Z)
• Physics simulation capabilities of LLMs [0.0]
  Large Language Models (LLMs) can solve some undergraduate-level to graduate-level physics textbook problems and are proficient at coding. We present an evaluation of state-of-the-art (SOTA) LLMs on PhD-level to research-level computational physics problems.
  arXiv  Detail & Related papers  (2023-12-04T18:06:41Z)
• Using Large Language Model to Solve and Explain Physics Word Problems Approaching Human Level [0.0]
  Large language model (LLM) pre-trained on texts can not only solve pure math word problems, but also physics word problems. Our work is the first research to focus on the automatic solving, explanation, and generation of physics word problems.
  arXiv  Detail & Related papers  (2023-09-15T06:13:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.