# TaoD2C-Bench: Benchmarking MLLMs for Industrial UI Code Generation Beyond Visual Fidelity

> TaoD2C-Bench reconstructs interfaces from design images, layer metadata and component-library documentation. It separates requirement inference from implementation, checking component choices and layout relations through source/runtime evidence alongside rendered appearance.

- Authors: Chengwei Shi; Yunnong Chen; Tingting Zhou; Qiang Lu; Shiyu Yue; Xinyuan Hu; Jianfang Ru; Liuqing Chen
- Venue: arXiv
- Status: Preprint
- Publication / posting date: October 7, 2026
- Date source: arXiv v1 submission date; no separate proceedings or journal publication was verified.
- First arXiv submission: October 7, 2026
- arXiv: 2610.10374
- Reviewed arXiv version: v1
- DOI: 10.48550/arXiv.2610.10374
- Sources reviewed: 2026-10-20
- Added to the catalog: 2026-10-20
- Original paper: <https://arxiv.org/abs/2610.10374>
- PDF: <https://arxiv.org/pdf/2610.10374v1>
- Project: <https://taod2c-bench.github.io/>
- BibTeX: <https://awesomerea.org/papers/citations/paper-taod2c-bench.bib>
- Catalog page: <https://awesomerea.org/papers/paper-taod2c-bench/>
- Record JSON: <https://awesomerea.org/papers/paper-taod2c-bench/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-taod2c-bench/index.md)

## Scope and limitations

Eight models are evaluated on 421 designs, not the full 2,861-design collection. Results include specified retries and one output-repair attempt. The tasks assess component/layout constraints and visual fidelity, not complete application behavior; all designs come from one commercial ecosystem.

## Why it fits this collection

Adds requirement-level checks for screenshot- and metadata-guided interface reconstruction.

## Publication and review notes

The linked repository at d4547c4 contains evaluation JSON only; no scorer or license file was found. Paper Appendix F assigns CC BY-NC 4.0 to annotations and separate restrictive terms to platform-owned assets.

## Primary sources

1. <https://arxiv.org/abs/2610.10374v1>
2. <https://arxiv.org/html/2610.10374v1>
3. <https://taod2c-bench.github.io/>
4. <https://github.com/TaoD2C-Bench/TaoD2C-Bench/tree/d4547c4d556d62dd01a73a9b1387a7e8477363bd>

## 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.