FEM-Bench: A Structured Scientific Reasoning Benchmark for Evaluating Code-Generating LLMs 事件

FEM-Bench: A Structured Scientific Reasoning Benchmark for Evaluating Code-Generating LLMs arXiv:2512.20732v2 Announce Type: replace-cross Abstract: As LLMs advance their reasoning capabilities about the physical world, the absence of rigorous benchmarks for evaluating their ability to generate scientifically valid physical models has become a critical gap. Computational mechanics, which develops and applies mathematical models and numerical methods to predict the behavior of physical systems u