@article{fembenchastructuredscientificreasoningbe,
  title = {FEM-Bench: A Structured Scientific Reasoning Benchmark for Evaluating Code-Generating LLMs},
  author = {Saeed Mohammadzadeh and Erfan Hamdi and Joel Shor and Emma Lejeune},
  year = {2025},
  eprint = {2512.20732},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.20732},
}