multimodal benchmark
Design2Code Leaderboard
Design2Code evaluates the ability to generate HTML/CSS/JS code from visual designs.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
Design2Code Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelZA | Score0.95 points | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score0.93 points | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
Design2Code Highlights
The leading models and scores on this benchmark.
Design2Code Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Design2Code
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Design2Code?
What Design2Code measures and how its scores work.
Design2Code is a multimodal benchmark for generating HTML/CSS/JS code from visual designs.
It measures the ability to generate HTML/CSS/JS code from visual designs, reported as Score in points.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- Design2Code
- Modality
- image
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Design2Code.
Which model scores highest on Design2Code?
GLM-5V-Turbo is currently ranked first with 0.95 points.
What are the top three models on Design2Code?
The current leaders are GLM-5V-Turbo (0.95 points) and Qwen3 VL 235B A22B Thinking (0.93 points).
Which Design2Code model has the lowest official input price?
GLM-5V-Turbo has the lowest matched official input price at $5.0 input / $22 output per 1M tokens.
Which models are fastest among Design2Code results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.