Metraipolis › archive › dc_b96a49ec4167
Comparing the Quality of Code Generated by Vibe Coding Tools — arXiv:2608.16302
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16302
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:55:28.270Z
- SHA-256 of the archived text
7c6ed6f80ddc42f7128bf30b1f7866a1f87aa7b158ebf0d29307713ead584f60- Stable URL of this page
https://metraipolis.com/documento/dc_b96a49ec4167
How to cite
Comparing the Quality of Code Generated by Vibe Coding Tools — arXiv:2608.16302 — arXiv (en), https://arxiv.org/abs/2608.16302 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b96a49ec4167 (Metraipolis archive dc_b96a49ec4167, sha256 7c6ed6f80ddc42f7128bf30b1f7866a1f87aa7b158ebf0d29307713ead584f60)
BibTeX
@misc{dcb96a49ec4167,
title = {Comparing the Quality of Code Generated by Vibe Coding Tools — arXiv:2608.16302},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16302},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b96a49ec4167; sha256 7c6ed6f80ddc42f7128bf30b1f7866a1f87aa7b158ebf0d29307713ead584f60},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16302. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The use of AI agents for automatic code generation has become increasingly common in software development. However, concerns remain about the quality of the generated code, including aspects of maintainability, readability, and long-term evolution. This study compares the structural quality of code produced by three widely adopted vibe coding tools --- Lovable, v0, and Replit --- starting from a single generation prompt. We generate three independent projects per tool, totalling nine web applications, and submit them to static analysis with SonarQube. We collect metrics such as the number of issues, severity distribution, estimated remediation effort, cyclomatic and cognitive complexity, and code duplication. Preliminary results show that the tools exhibit distinct qualitative profiles: Lovable concentrates issues of lower severity but presents a substantially higher density of code smells per KLOC, while v0 and Replit produce more code with more aggressive severity profiles. These findings suggest that choosing between vibe coding tools involves structural trade-offs that go beyond perceived productivity. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-18 in cs.SE). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.16302 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T19:41:47.862Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).