# Generating Energy-Efficient Code via Large-Language Models -- Where are we now?

arXiv: https://arxiv.org/abs/2509.10099 · HTML: https://mlsanity.com/paper/2509.10099/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 79 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Development](https://mlsanity.com/paper/2302.07080/) (2023)
- [A Systematic Review of Green AI](https://mlsanity.com/paper/2301.11047/) (2023)
- [A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges](https://mlsanity.com/paper/2303.17125/) (2023)
- [Towards an Understanding of Large Language Models in Software Engineering Tasks](https://mlsanity.com/paper/2308.11396/) (2023)
- [EffiBench: Benchmarking the Efficiency of Automatically Generated Code](https://mlsanity.com/paper/2402.02037/) (2024)
- [A Performance Study of LLM-Generated Code on Leetcode](https://mlsanity.com/paper/2407.21579/) (2024)
- [Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forward](https://mlsanity.com/paper/2406.07765/) (2024)
- [An Aligned Rank Transform Procedure for Multifactor Contrast Tests](https://mlsanity.com/paper/2102.11824/) (2021)
- [Generative AI and Empirical Software Engineering: A Paradigm Shift](https://mlsanity.com/paper/2502.08108/) (2025)
- [AI-Powered, But Power-Hungry? Energy Efficiency of LLM-Generated Code](https://mlsanity.com/paper/2502.02412/) (2025)
- [LLMs for Generation of Architectural Components: An Exploratory Empirical Study in the Serverless World](https://mlsanity.com/paper/2502.02539/) (2025)
- [Evaluation of large language models for assessing code maintainability](https://mlsanity.com/paper/2401.12714/) (2024)
- [Unveiling the Energy Vampires: A Methodology for Debugging Software Energy Consumption](https://mlsanity.com/paper/2412.10063/) (2024)
- [Estimating the Energy Footprint of Software Systems: a Primer](https://mlsanity.com/paper/2407.11611/) (2024)
- [GPU Computing with Python: Performance, Energy Efficiency and Usability](https://mlsanity.com/paper/1912.02607/) (2019)
- [Toward Efficient Interactions between Python and Native Libraries](https://mlsanity.com/paper/2107.00064/) (2021)
- [Reproducibility, energy efficiency and performance of pseudorandom number generators in machine learning: a comparative study of python, numpy, tensorflow, and pytorch implementations](https://mlsanity.com/paper/2401.17345/) (2024)

## Built on by (most cited first, 6 of 6)

- [SWEnergy: An Empirical Study on Energy Efficiency in Agentic Issue Resolution Frameworks with SLMs](https://mlsanity.com/paper/2512.09543/) (2025)
- [GA4GC: Greener Agent for Greener Code via Multi-Objective Configuration Optimization](https://mlsanity.com/paper/2510.04135/) (2025)
- [Towards Green AI: Decoding the Energy of LLM Inference in Software Development](https://mlsanity.com/paper/2602.05712/) (2026)
- [An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code](https://mlsanity.com/paper/2604.02352/) (2026)
- [Characterizing the Quality Profile of AI-Generated C++ in Production](https://mlsanity.com/paper/2608.06640/) (2026)
- [Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting](https://mlsanity.com/paper/2610.02571/) (2026)

## Abstract (arXiv)

Context. The rise of Large Language Models (LLMs) has led to their widespread adoption in development pipelines. Goal. We empirically assess the energy efficiency of Python code generated by LLMs against human-written code and code developed by a Green software expert. Method. We test 363 solutions to 9 coding problems from the EvoEval benchmark using 6 widespread LLMs with 4 prompting techniques, and comparing them to human-developed solutions. Energy consumption is measured on three different hardware platforms: a server, a PC, and a Raspberry Pi for a total of ~881h (36.7 days). Results. Human solutions are 16% more energy-efficient on the server and 3% on the Raspberry Pi, while LLMs outperform human developers by 25% on the PC. Prompting does not consistently lead to energy savings, where the most energy-efficient prompts vary by hardware platform. The code developed by a Green software expert is consistently more energy-efficient by at least 17% to 30% against all LLMs on all hardware platforms. Conclusions. Even though LLMs exhibit relatively good code generation capabilities, no LLM-generated code was more energy-efficient than that of an experienced Green software developer, suggesting that as of today there is still a great need of human expertise for developing energy-efficient Python code.