---
title: "Comparative Analysis of Carbon Footprint in Manual vs. LLM-Assisted Code Development"
description: "Large language models now help write a great deal of code, but they use energy in training and in every request. This paper compares the energy, and so the…"
url: https://greencode.ai/publications/greencode-for-generative-ai-wp3/
---

# Comparative Analysis of Carbon Footprint in Manual vs. LLM-Assisted Code Development

- **Authors:** [Kuen Sum Cheung](https://orcid.org/0009-0003-5646-3047 "ORCID profile of Kuen Sum Cheung") , [Mayuri Kaul](https://orcid.org/0009-0007-2033-340X "ORCID profile of Mayuri Kaul") , [Gunel Jahangirova](https://orcid.org/0000-0002-1423-1083 "ORCID profile of Gunel Jahangirova") , [Mohammad Reza Mousavi](https://orcid.org/0000-0002-4869-6794 "ORCID profile of Mohammad Reza Mousavi") , [Eric Zie](https://orcid.org/0009-0007-9683-0760 "ORCID profile of Eric Zie")
- **Contributing partner:** [King's College London](https://greencode.ai/partners/king-s-college-london/ "King's College London in GreenCode")
- **Published in:** Proceedings of the 1st International Workshop on Responsible Software Engineering (ResponsibleSE 2025), ACM
- **Published:** Jun 2025
- **Type:** Paper
- **DOI:** [10.1145/3711919.3728678](https://doi.org/10.1145/3711919.3728678)

### Synopsis

Large language models now help write a great deal of code, but they use energy in training and in every request. This paper compares the energy, and so the carbon footprint, of solving programming tasks by hand with solving them with an LLM assistant, using Codeforces problems as a controlled stand-in for everyday development. Averaged across the tasks, LLM-assisted code generation had 32.72 times the carbon footprint of the manual approach, and the gap widened as tasks became more complex. The authors propose ways to reduce the footprint of LLM-assisted development, a question at the heart of GreenCode's own use of AI.

[View at the publisher](https://doi.org/10.1145/3711919.3728678) [All publications](https://greencode.ai/publications/)Cite this work

(2025). GreenCode for Generative AI (WP3). GreenCode for Generative AI (WP3). [https://sites.google.com/view/responsible-se/accepted-papers](https://sites.google.com/view/responsible-se/accepted-papers?utm_source=greencode.ai&utm_medium=referral&utm_campaign=greencode)
