SOURCE-LINKED INTELLIGENCE
Scientific Coding with Large Language Models: Evidence from Finite Element Analysis
Large language models (LLMs) offer a potential route to automating scientific programming, but their usefulness depends on consistently producing numerically correct code. We extend FEM-Bench to 17 finite element tasks involving nonlinear and history-dependent mechanics and structural dynamics, and evaluate 15 models on implementation and test generation without execution feedback. The best model succeeds in 87.1% of single-pass implementation trials, but rankings differ between tracks. The leading implementer achieves 49.9% joint test success, while the leading tester reaches 82.6%. For six m
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-11-16T14:35:30.000Z
First collected: 2026-11-17T10:01:33.465Z. This is not the publication date.