1
Beyond Pass Rate: A Multilingual, Execution-Grounded Evaluation of Open Code LLMs
从单纯通过率到多语言执行评估，这篇论文重新定义了开源代码大模型的性能比较标准。
arXiv:2606.08840v1 Announce Type: new Abstract: Code generation models are typically compared using compact execution benchmarks and aggregate pass ra…