SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code
Uloženo v:
| Název: | SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code |
|---|---|
| Autoři: | Imani, Shima, Moon, Seungwhan, Ahmadyan, Adel, Zhang, Lu, Ahmed, Kirmani, Damavandi, Babak |
| Rok vydání: | 2025 |
| Sbírka: | ArXiv.org (Cornell University Library) |
| Témata: | Artificial Intelligence |
| Popis: | 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 |
| Druh dokumentu: | text |
| Jazyk: | unknown |
| Relation: | http://arxiv.org/abs/2512.05954 |
| Dostupnost: | http://arxiv.org/abs/2512.05954 |
| Přístupové číslo: | edsbas.84F3A2E3 |
| Databáze: | BASE |
Nájsť tento článok vo Web of Science Buďte první, kdo okomentuje tento záznam!