multimodal benchmark
Vision2Web Leaderboard
Vision2Web evaluates multimodal models on converting visual designs and screenshots into functional web pages.
Updated Sep 5, 2026
Models5
Model coverage5
MetricScore
EvidenceB
Vision2Web Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score69.00% | Percentile100.00% | Participants5 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score64.00% | Percentile75.00% | Participants5 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score64.00% | Percentile50.00% | Participants5 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score62.90% | Percentile25.00% | Participants5 | EvidenceC | Evaluated |
| Rank05 | ModelZA | Score31.00% | Percentile0.00% | Participants5 | EvidenceC | Evaluated |
Vision2Web Highlights
The leading models and scores on this benchmark.
Vision2Web Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Vision2Web
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Vision2Web?
What Vision2Web measures and how its scores work.
Vision2Web is a multimodal benchmark for evaluating the conversion of visual designs and screenshots into functional web pages.
It measures end-to-end design-to-code capability using the Score metric, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Vision2Web
- Modality
- multimodal
- 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 Vision2Web.
Which model scores highest on Vision2Web?
Qwen3.8 Max is currently ranked first with 69.00%.
What are the top three models on Vision2Web?
The current leaders are Qwen3.8 Max (69.00%), Qwen3.8-Flash-Next (64.00%), and Qwen3.8 Flash (64.00%).
Which Vision2Web model has the lowest official input price?
Qwen3.8 Flash has the lowest matched official input price at $0.15 input / $0.47 output per 1M tokens.
Which models are fastest among Vision2Web results?
The fastest matched records are Qwen3.8 Max (60.87 tok/s via DeepInfra).
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.