@article{compassamultidimensionalbenchmarkforeval, title = {COMPASS: A Multi-Dimensional Benchmark for Evaluating Code Generation in Large Language Models}, author = {James Meaden and Michał Jarosz and Piotr Jodłowski and Grigori Melnik}, year = {2025}, eprint = {2508.13757}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.13757}, }