MMS ci C ode: Real-world Evaluation of Multilingual Multi-Discipline Scientific Research Coding
Xue Xia · Zheyuan Yang · Arman Cohan · Yilun Zhao
摘要
We introduce MMSciCode, a comprehensive expert-level, multilingual multi-discipline benchmark for evaluating foundation models in scientific code generation. It includes 624 expert-annotated research coding problems spanning six core scientific disciplines. Compared to prior benchmarks, MMSciCode...