# Image-to-Web Conversion on IW-BENCH Medium

Source: [Image-to-Web Conversion on IW-BENCH Medium](<https://www.sota2.com/research/sota/image-to-web-conversion-on-iw-bench-medium>)

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

Data updated: 2026-02-26T05:41:56.801Z

Evaluation of Image-to-Web Conversion performance on the IW-BENCH Medium dataset, assessed using Element Accuracy and Layout Accuracy.

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 | Image-to-Web Conversion |
| Dataset (including any stated split) | IW-BENCH Medium |
| Metric | Element Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Element Accuracy](<https://www.sota2.com/research/sota/image-to-web-conversion-on-iw-bench-medium.md?metric=Element%20Accuracy>): Higher is better; unit: PERCENT.

- [Layout Accuracy](<https://www.sota2.com/research/sota/image-to-web-conversion-on-iw-bench-medium.md?metric=Layout%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Element Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| WebSight | 0.502 | Not recorded | 68fa74f81e209131cea64f12 |
| Qwen-VL-Max | 0.472 | Not recorded | 68fa74f81e209131cea64f12 |
| GPT4V | 0.431 | Not recorded | 68fa74f81e209131cea64f12 |
| Gemini Pro | 0.425 | Not recorded | 68fa74f81e209131cea64f12 |
| Claude 3 Opus | 0.378 | Not recorded | 68fa74f81e209131cea64f12 |
| Qwen-VL-Max | 0.369 | Not recorded | 68fa74f81e209131cea64f12 |
| Gemini Pro | 0.341 | Not recorded | 68fa74f81e209131cea64f12 |
| Claude 3 Opus | 0.301 | Not recorded | 68fa74f81e209131cea64f12 |
| LLAVA-LLAMA-2-13B | 0.278 | Not recorded | 68fa74f81e209131cea64f12 |
| GPT4V | 0.274 | Not recorded | 68fa74f81e209131cea64f12 |
| Qwen-VL-Plus | 0.252 | Not recorded | 68fa74f81e209131cea64f12 |
| Qwen-VL-Chat | 0.241 | Not recorded | 68fa74f81e209131cea64f12 |
| LLaVA-LLaMA-2-13B | 0.189 | Not recorded | 68fa74f81e209131cea64f12 |
| MPLUG-OWL2 | 0.146 | Not recorded | 68fa74f81e209131cea64f12 |
| miniGPT-4-LLaMA-2-7B | 0.136 | Not recorded | 68fa74f81e209131cea64f12 |
| LLaMA-Adapter-V2-7B | 0.043 | Not recorded | 68fa74f81e209131cea64f12 |

### WebSight

Element Accuracy: 0.502. Result ID: 69936cf83a6c31484915d9ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Disabled"}. This record does not assert independent reproduction.

### Qwen-VL-Max

Element Accuracy: 0.472. Result ID: 69936cf83a6c31484915d9d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Enabled","MCoT Hops":5}. This record does not assert independent reproduction.

### GPT4V

Element Accuracy: 0.431. Result ID: 69936cf83a6c31484915d9cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Enabled","MCoT Hops":5}. This record does not assert independent reproduction.

### Gemini Pro

Element Accuracy: 0.425. Result ID: 69936cf83a6c31484915d9d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Enabled","MCoT Hops":5}. This record does not assert independent reproduction.

### Claude 3 Opus

Element Accuracy: 0.378. Result ID: 69936cf83a6c31484915d9d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Enabled","MCoT Hops":5}. This record does not assert independent reproduction.

### Qwen-VL-Max

Element Accuracy: 0.369. Result ID: 69936cf83a6c31484915d9c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Disabled"}. This record does not assert independent reproduction.

### Gemini Pro

Element Accuracy: 0.341. Result ID: 69936cf83a6c31484915d9cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Disabled"}. This record does not assert independent reproduction.

### Claude 3 Opus

Element Accuracy: 0.301. Result ID: 69936cf83a6c31484915d9cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Disabled"}. This record does not assert independent reproduction.

### LLAVA-LLAMA-2-13B

Element Accuracy: 0.278. Result ID: 69936cf83a6c31484915d9d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Enabled","MCoT Hops":5}. This record does not assert independent reproduction.

### GPT4V

Element Accuracy: 0.274. Result ID: 69936cf83a6c31484915d9c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Disabled"}. This record does not assert independent reproduction.

### Qwen-VL-Plus

Element Accuracy: 0.252. Result ID: 69936cf83a6c31484915d9c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Disabled"}. This record does not assert independent reproduction.

### Qwen-VL-Chat

Element Accuracy: 0.241. Result ID: 69936cf83a6c31484915d9c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Disabled"}. This record does not assert independent reproduction.

### LLaVA-LLaMA-2-13B

Element Accuracy: 0.189. Result ID: 69936cf83a6c31484915d9c8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

[Implementation](<https://llava-vl.github.io/>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Disabled"}. This record does not assert independent reproduction.

### MPLUG-OWL2

Element Accuracy: 0.146. Result ID: 69936cf83a6c31484915d9ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ae1e209131cea57d83.md>)

[Implementation](<https://github.com/X-PLUG/mPLUG-Owl>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Disabled"}. This record does not assert independent reproduction.

### miniGPT-4-LLaMA-2-7B

Element Accuracy: 0.136. Result ID: 69936cf83a6c31484915d9c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70bd1e209131cea4cf90.md>)

[Implementation](<https://minigpt-4.github.io/>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Disabled"}. This record does not assert independent reproduction.

### LLaMA-Adapter-V2-7B

Element Accuracy: 0.043. Result ID: 69936cf83a6c31484915d9cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74f81e209131cea64f12.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f331e209131cea4463a.md>)

[Implementation](<https://github.com/ZrrSkywalker/LLaMA-Adapter>)

Recorded evaluation configuration: {"Chain-of-Thought (MCoT) status":"Disabled"}. This record does not assert independent reproduction.

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