REVIEW 5 cited by
UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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 .
Forward citations
Cited by 5 Pith papers
-
SPM-Bench: Benchmarking Large Language Models for Scanning Probe Microscopy
A new benchmark of 2,703 automatically generated multimodal questions for scanning probe microscopy, plus a modified F1 metric that penalizes over-selection and labels model 'personalities'.
-
DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning
A unified visual benchmark of six physics environments shows current VLMs, including frontier models, mostly fail at interactive physical reasoning and cannot convert descriptive physics knowledge into reliable control.
-
Superstudent intelligence in thermodynamics
OpenAI's o3 model scored higher than all 90 students on a real university thermodynamics exam, zero-shot, including problems with graphical output.
-
PhySense: Principle-Based Physics Reasoning Benchmarking for Large Language Models
A new benchmark of 380 principle-based physics problems shows that state-of-the-art LLMs struggle to apply symmetry, conservation, and dimensional-analysis shortcuts, achieving under 50 percent average accuracy with h...
-
PhyX: Does Your Model Have the "Wits" for Physical Reasoning?
PhyX is a new 3,000-question visual physics benchmark; the best AI model tested scores 45.8 percent, well below the 75.6 to 78.9 percent of a small human student sample.
Discussion (0). Continue with ORCID to comment.