# Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering

> Evaluates reconstruction of frontend code from webpage screenshots using real-world reference pages, visual-element and layout metrics, and human assessment.

- Authors: Chenglei Si; Yanzhe Zhang; Ryan Li; Zhengyuan Yang; Ruibo Liu; Diyi Yang
- Venue: NAACL 2025
- Status: Conference paper
- Publication / posting date: April 2025
- Date source: ACL proceedings publication month
- First arXiv submission: March 5, 2024
- arXiv: 2403.03163
- Reviewed arXiv version: v3
- DOI: 10.18653/v1/2025.naacl-long.199
- Sources reviewed: 2026-10-17
- Added to the catalog: 2026-10-16
- Original paper: <https://aclanthology.org/2025.naacl-long.199/>
- PDF: <https://aclanthology.org/2025.naacl-long.199.pdf>
- Code: <https://github.com/NoviScl/Design2Code>
- Project: <https://salt-nlp.github.io/Design2Code/>
- BibTeX: <https://awesomerea.org/papers/citations/paper-design2code.bib>
- Catalog page: <https://awesomerea.org/papers/paper-design2code/>
- Record JSON: <https://awesomerea.org/papers/paper-design2code/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-design2code/index.md)

## Scope and limitations

This is visual website reconstruction, not binary decompilation or recovery of backend behavior and interactive workflows. The main benchmark contains 484 webpages with placeholder images; code and data have separate licensing terms.

## Why it fits this collection

Directly supports the collection's screenshot-to-website reconstruction scope while keeping visual fidelity separate from behavioral equivalence.

## Publication and review notes

Use the final NAACL 2025 title and six-author list. arXiv v1 (2024-03-05) and the project page’s BibTeX use the earlier title “Design2Code: How Far Are We From Automating Front-End Engineering?” and list five authors without Ryan Li; v2 and the reviewed v3 match the final title and authors. SALT-NLP/Design2Code hosts the project website, whereas NoviScl/Design2Code is the verified research-code repository.

## Primary sources

1. <https://aclanthology.org/2025.naacl-long.199/>
2. <https://aclanthology.org/2025.naacl-long.199.pdf>
3. <https://arxiv.org/abs/2403.03163>
4. <https://arxiv.org/abs/2403.03163v1>
5. <https://salt-nlp.github.io/Design2Code/>
6. <https://github.com/NoviScl/Design2Code>
7. <https://github.com/NoviScl/Design2Code/blob/7a575e4c33f417c4be5c64072b8f5798de0d0f99/README.md>

## About this entry

Reviewed against the paper and its primary sources. Cite the original authors using the linked paper or BibTeX.
Original editorial content: MIT. Linked projects, papers and assets retain their own rights and licenses.