SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Imani, Shima, Moon, Seungwhan, Ahmadyan, Adel, Zhang, Lu, Ahmed, Kirmani, Damavandi, Babak
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915657155608576
author Imani, Shima
Moon, Seungwhan
Ahmadyan, Adel
Zhang, Lu
Ahmed, Kirmani
Damavandi, Babak
author_facet Imani, Shima
Moon, Seungwhan
Ahmadyan, Adel
Zhang, Lu
Ahmed, Kirmani
Damavandi, Babak
contents We introduce, a large-scale synthetic benchmark of 15,045 university-level physics problems (90/10% train/test split). Each problem is fully parameterized, supporting an effectively infinite range of input configurations, and is accompanied by structured, step-by-step reasoning and executable Python code that produces the ground-truth solution for any parameter set. The benchmark contains three question types: MC-Symbolic (multiple-choice with symbolic options), MC-Numerical (multiple-choice with numerical options), and free-form (open-ended responses). These diverse formats test complementary reasoning skills. By leveraging the dynamic, code-driven nature of the benchmark, we introduce three novel evaluation metrics in addition to standard accuracy: Consistency Score, Failure Rate, and Confusion Rate, that quantify variability and uncertainty across problem variants. Experiments with state-of-the-art instruction-tuned language models reveal both strengths and limitations in scientific reasoning, positioning SymPyBench as a foundation for developing more robust and interpretable reasoning systems
format Preprint
id arxiv_https___arxiv_org_abs_2512_05954
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code
Imani, Shima
Moon, Seungwhan
Ahmadyan, Adel
Zhang, Lu
Ahmed, Kirmani
Damavandi, Babak
Artificial Intelligence
We introduce, a large-scale synthetic benchmark of 15,045 university-level physics problems (90/10% train/test split). Each problem is fully parameterized, supporting an effectively infinite range of input configurations, and is accompanied by structured, step-by-step reasoning and executable Python code that produces the ground-truth solution for any parameter set. The benchmark contains three question types: MC-Symbolic (multiple-choice with symbolic options), MC-Numerical (multiple-choice with numerical options), and free-form (open-ended responses). These diverse formats test complementary reasoning skills. By leveraging the dynamic, code-driven nature of the benchmark, we introduce three novel evaluation metrics in addition to standard accuracy: Consistency Score, Failure Rate, and Confusion Rate, that quantify variability and uncertainty across problem variants. Experiments with state-of-the-art instruction-tuned language models reveal both strengths and limitations in scientific reasoning, positioning SymPyBench as a foundation for developing more robust and interpretable reasoning systems
title SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code
topic Artificial Intelligence
url https://arxiv.org/abs/2512.05954