2026 · Preprint
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.
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 details
- 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
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. No data assets or code were executed or downloaded.
Sources reviewed
Source review only; experiments were not rerun for this collection. Cite the original authors using the linked paper or BibTeX.