
Generating Energy-Efficient Code via Large-Language Models - Where are we now?
24-Sep-2025
We are excited to announce that a paper by the Software and Sustainability research group and colleagues has been accepted at the International Conference on Software Engineering (ICSE 2026), the premier conference in software engineering!
Title: Generating Energy-Efficient Code via Large-Language Models â Where are we now?
Authors: Radu Apsan, Vincenzo Stoico, Michel Albonico, Rudra Dhar, Karthik Vaidhyanathan, and Ivano Malavolta.
đ Read the paper here
đĄ Key Findings
- đĸ Human expert code remains the most energy-efficient, outperforming all LLM-generated code by 17% to 30%.
- đ¤ LLMs outperform average human developers on some platforms, but still lag behind green-expert solutions.
- âī¸ Prompt engineering does not consistently improve energy efficiency.
- đŠī¸ Human expertise is still crucial for developing energy-efficient Python code.