# Webpage Generation and Editing on DesignBench

Source: [Webpage Generation and Editing on DesignBench](<https://www.sota2.com/research/sota/webpage-generation-and-editing-on-designbench>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-15T07:22:12.298Z

Evaluation of models performing Webpage Generation and Editing tasks using the DesignBench dataset, assessed via generation and editing specific metrics.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Webpage Generation and Editing |
| Dataset (including any stated split) | DesignBench |
| Metric | Generation Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Generation Score](<https://www.sota2.com/research/sota/webpage-generation-and-editing-on-designbench.md?metric=Generation%20Score>): Higher is better; unit: SCALAR.

- [Editing Score](<https://www.sota2.com/research/sota/webpage-generation-and-editing-on-designbench.md?metric=Editing%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Generation Score | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4o | 76.83 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| JANUSCODERV-7B | 73.31 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| Qwen2.5-VL-7B-Ins | 72.73 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| InternVL3.5-8B | 71.73 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| InternVL3-8B | 69.34 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| JANUSCODERV-8B | 68.86 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| MiniCPM-V-2-6 | 66.25 | Not recorded | 69004e143ef7ccd74e5e2e9e |
| Llama-3.2-11B-Vision-Ins | 62.24 | Not recorded | 69004e143ef7ccd74e5e2e9e |

### GPT-4o

Generation Score: 76.83. Result ID: 69df3c5f47f34ce924c79b68.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a98.md>)

Recorded evaluation configuration: {"License":"Proprietary"}. This record does not assert independent reproduction.

### JANUSCODERV-7B

Generation Score: 73.31. Result ID: 69df3c5f47f34ce924c79b66.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B-Ins

Generation Score: 72.73. Result ID: 69df3c5f47f34ce924c79b61.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### InternVL3.5-8B

Generation Score: 71.73. Result ID: 69df3c5f47f34ce924c79b63.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af01e209131cea85dc9.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### InternVL3-8B

Generation Score: 69.34. Result ID: 69df3c5f47f34ce924c79b62.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### JANUSCODERV-8B

Generation Score: 68.86. Result ID: 69df3c5f47f34ce924c79b67.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### MiniCPM-V-2-6

Generation Score: 66.25. Result ID: 69df3c5f47f34ce924c79b64.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74681e209131cea6183d.md>)

[Implementation](<https://github.com/OpenBMB/MiniCPM-V>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

### Llama-3.2-11B-Vision-Ins

Generation Score: 62.24. Result ID: 69df3c5f47f34ce924c79b65.

[Reporting paper](<https://www.sota2.com/research/paper/69004e143ef7ccd74e5e2e9e.md>)

Recorded evaluation configuration: {"License":"Open-Source"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.