Mercury: ACodeEfficiencyBenchmarkforCode LargeLanguageModels
–Neural Information Processing Systems
Amidst therecent strides inevaluating LargeLanguage Models forCode (Code LLMs), existing benchmarks havemainly focused onthefunctional correctness of generated code, neglecting the importance of their computational efficiency.
Neural Information Processing Systems
Feb-9-2026, 02:14:23 GMT
- Country:
- Asia
- China > Jiangsu Province
- Changzhou (0.04)
- Singapore (0.04)
- China > Jiangsu Province
- Europe > France (0.04)
- North America > United States (0.04)
- Asia
- Genre:
- Research Report > New Finding (0.68)
- Industry:
- Information Technology > Security & Privacy (0.46)
- Technology: