Benchmark
Design2Code
Design2Code evaluates the ability to generate code (HTML/CSS/JS) from visual designs.
- Modality
- image
- Categories
- multimodal, code, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 2
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GLM-5V-Turbo | Z.ai | 0.948 | 2026-04-02 | evidence |
| Qwen3 VL 235B A22B Thinking | Qwen | 0.934 | 2025-09-22 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.