# HTML UI Generation on Cookie-Bench Static split

Source: [HTML UI Generation on Cookie-Bench Static split](<https://www.sota2.com/research/sota/html-ui-generation-on-cookie-bench-static-split>)

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

Data updated: 2026-05-29T10:43:44.732Z

Evaluation of model performance on generating HTML User Interfaces using the static split of the Cookie-Bench dataset, measured by Functionality, Aesthetics, and Total scores.

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 | HTML UI Generation |
| Dataset (including any stated split) | Cookie-Bench Static split |
| Metric | Functionality Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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

- [Functionality Score](<https://www.sota2.com/research/sota/html-ui-generation-on-cookie-bench-static-split.md?metric=Functionality%20Score>): Higher is better; unit: PERCENT.

- [Aesthetics Score](<https://www.sota2.com/research/sota/html-ui-generation-on-cookie-bench-static-split.md?metric=Aesthetics%20Score>): Higher is better; unit: PERCENT.

- [Total Score](<https://www.sota2.com/research/sota/html-ui-generation-on-cookie-bench-static-split.md?metric=Total%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Functionality Score | Result date | Report paper |
| --- | --- | --- | --- |
| Opus 4.7 | 90.9 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| GPT-5.4 | 88.1 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| Opus 4.6 | 82.7 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| DS-V4-Flash | 81.4 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| Mimo-V2-Pro | 81 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| Gemini-3.1-Pro | 80.9 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| GLM-5.1 | 80.4 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| Qwen3.6-Plus | 79.8 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| Kimi-K2.6 | 78.9 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| Qwen3.6-27B | 78.6 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| Gemini-3-Flash | 78.1 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| Qwen3.6-35B-A3B | 74.6 | Not recorded | 6a191ddfdbd7150506f82ba8 |
| DS-V4-Pro | 71.9 | Not recorded | 6a191ddfdbd7150506f82ba8 |

### Opus 4.7

Functionality Score: 90.9. Result ID: 6a196ce7fbc373592c14786f.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### GPT-5.4

Functionality Score: 88.1. Result ID: 6a196ce7fbc373592c14786c.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### Opus 4.6

Functionality Score: 82.7. Result ID: 6a196ce7fbc373592c14786e.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### DS-V4-Flash

Functionality Score: 81.4. Result ID: 6a196ce7fbc373592c147867.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### Mimo-V2-Pro

Functionality Score: 81. Result ID: 6a196ce7fbc373592c14786b.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### Gemini-3.1-Pro

Functionality Score: 80.9. Result ID: 6a196ce7fbc373592c147865.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### GLM-5.1

Functionality Score: 80.4. Result ID: 6a196ce7fbc373592c14786a.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### Qwen3.6-Plus

Functionality Score: 79.8. Result ID: 6a196ce7fbc373592c147869.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### Kimi-K2.6

Functionality Score: 78.9. Result ID: 6a196ce7fbc373592c14786d.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### Qwen3.6-27B

Functionality Score: 78.6. Result ID: 6a196ce7fbc373592c147866.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### Gemini-3-Flash

Functionality Score: 78.1. Result ID: 6a196ce7fbc373592c147864.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### Qwen3.6-35B-A3B

Functionality Score: 74.6. Result ID: 6a196ce7fbc373592c147863.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

### DS-V4-Pro

Functionality Score: 71.9. Result ID: 6a196ce7fbc373592c147868.

[Reporting paper](<https://www.sota2.com/research/paper/6a191ddfdbd7150506f82ba8.md>)

Recorded evaluation configuration: {"Generation Mode":"HTML direct chat"}. This record does not assert independent reproduction.

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