# GUI Localization on GUIZoom-Bench hard-mislead

Source: [GUI Localization on GUIZoom-Bench hard-mislead](<https://www.sota2.com/research/sota/gui-localization-on-guizoom-bench-hard-mislead>)

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

Data updated: 2026-02-27T11:50:13.224Z

Evaluation of model performance on the hard-mislead split of the GUIZoom-Bench dataset for GUI Localization tasks, measured by Localization 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 | GUI Localization |
| Dataset (including any stated split) | GUIZoom-Bench hard-mislead |
| Metric | Localization Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 29 of 29 |
| 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

- [Localization Accuracy](<https://www.sota2.com/research/sota/gui-localization-on-guizoom-bench-hard-mislead.md?metric=Localization%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Localization Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3-VL-32B | 54.1 | Not recorded | 69365b83d6b0dd3342934c20 |
| Qwen3-VL-8B | 45.9 | Not recorded | 69365b83d6b0dd3342934c20 |
| Qwen3-VL-32B | 45.9 | Not recorded | 69365b83d6b0dd3342934c20 |
| Qwen3-VL-32B | 45.9 | Not recorded | 69365b83d6b0dd3342934c20 |
| Qwen3-VL-8B | 40.5 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-Venus-7B | 35.1 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-Venus-7B | 35.1 | Not recorded | 69365b83d6b0dd3342934c20 |
| Qwen3-VL-8B | 32.4 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-Venus-7B | 29.7 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-TARS-7B | 24.3 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-TARS-1.5-7B | 24.3 | Not recorded | 69365b83d6b0dd3342934c20 |
| Qwen3-VL-32B | 21.6 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-TARS-1.5-7B | 21.6 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-TARS-7B | 18.9 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-TARS-1.5-7B | 18.9 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-TARS-1.5-7B | 18.9 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-Venus-7B | 18.9 | Not recorded | 69365b83d6b0dd3342934c20 |
| Qwen3-VL-8B | 16.2 | Not recorded | 69365b83d6b0dd3342934c20 |
| Qwen2.5-VL-7B | 16.2 | Not recorded | 69365b83d6b0dd3342934c20 |
| Qwen2.5-VL-7B | 13.5 | Not recorded | 69365b83d6b0dd3342934c20 |
| Qwen2.5-VL-7B | 10.8 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-TARS-7B | 10.8 | Not recorded | 69365b83d6b0dd3342934c20 |
| Claude-4.5-Sonnet | 10.5 | Not recorded | 69365b83d6b0dd3342934c20 |
| GPT-5 | 8.1 | Not recorded | 69365b83d6b0dd3342934c20 |
| GPT-5 | 5.4 | Not recorded | 69365b83d6b0dd3342934c20 |
| UI-TARS-7B | 5.4 | Not recorded | 69365b83d6b0dd3342934c20 |
| GPT-5 | 2.7 | Not recorded | 69365b83d6b0dd3342934c20 |
| GPT-5 | 0 | Not recorded | 69365b83d6b0dd3342934c20 |
| Qwen2.5-VL-7B | 0 | Not recorded | 69365b83d6b0dd3342934c20 |

### Qwen3-VL-32B

Localization Accuracy: 54.1. Result ID: 69a184e435dfcabb00e790f8.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d4"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

Localization Accuracy: 45.9. Result ID: 69a184e435dfcabb00e790f4.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Zoom Depth":"d4"}. This record does not assert independent reproduction.

### Qwen3-VL-32B

Localization Accuracy: 45.9. Result ID: 69a184e435dfcabb00e790f6.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d2"}. This record does not assert independent reproduction.

### Qwen3-VL-32B

Localization Accuracy: 45.9. Result ID: 69a184e435dfcabb00e790f7.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d3"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

Localization Accuracy: 40.5. Result ID: 69a184e435dfcabb00e790f3.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Zoom Depth":"d3"}. This record does not assert independent reproduction.

### UI-Venus-7B

Localization Accuracy: 35.1. Result ID: 69a184e435dfcabb00e79106.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d2"}. This record does not assert independent reproduction.

### UI-Venus-7B

Localization Accuracy: 35.1. Result ID: 69a184e435dfcabb00e79107.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d3"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

Localization Accuracy: 32.4. Result ID: 69a184e435dfcabb00e790f2.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Zoom Depth":"d2"}. This record does not assert independent reproduction.

### UI-Venus-7B

Localization Accuracy: 29.7. Result ID: 69a184e435dfcabb00e79108.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d4"}. This record does not assert independent reproduction.

### UI-TARS-7B

Localization Accuracy: 24.3. Result ID: 69a184e435dfcabb00e790ff.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a61e209131cea6e2ba.md>)

Recorded evaluation configuration: {"Zoom Depth":"d3"}. This record does not assert independent reproduction.

### UI-TARS-1.5-7B

Localization Accuracy: 24.3. Result ID: 69a184e435dfcabb00e79102.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a61e209131cea6e2ba.md>)

Recorded evaluation configuration: {"Zoom Depth":"d2"}. This record does not assert independent reproduction.

### Qwen3-VL-32B

Localization Accuracy: 21.6. Result ID: 69a184e435dfcabb00e790f5.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d1"}. This record does not assert independent reproduction.

### UI-TARS-1.5-7B

Localization Accuracy: 21.6. Result ID: 69a184e435dfcabb00e79103.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a61e209131cea6e2ba.md>)

Recorded evaluation configuration: {"Zoom Depth":"d3"}. This record does not assert independent reproduction.

### UI-TARS-7B

Localization Accuracy: 18.9. Result ID: 69a184e435dfcabb00e79100.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a61e209131cea6e2ba.md>)

Recorded evaluation configuration: {"Zoom Depth":"d4"}. This record does not assert independent reproduction.

### UI-TARS-1.5-7B

Localization Accuracy: 18.9. Result ID: 69a184e435dfcabb00e79101.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a61e209131cea6e2ba.md>)

Recorded evaluation configuration: {"Zoom Depth":"d1"}. This record does not assert independent reproduction.

### UI-TARS-1.5-7B

Localization Accuracy: 18.9. Result ID: 69a184e435dfcabb00e79104.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a61e209131cea6e2ba.md>)

Recorded evaluation configuration: {"Zoom Depth":"d4"}. This record does not assert independent reproduction.

### UI-Venus-7B

Localization Accuracy: 18.9. Result ID: 69a184e435dfcabb00e79105.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d1"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

Localization Accuracy: 16.2. Result ID: 69a184e435dfcabb00e790f1.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Zoom Depth":"d1"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Localization Accuracy: 16.2. Result ID: 69a184e435dfcabb00e790fb.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

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

Recorded evaluation configuration: {"Zoom Depth":"d3"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Localization Accuracy: 13.5. Result ID: 69a184e435dfcabb00e790fc.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

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

Recorded evaluation configuration: {"Zoom Depth":"d4"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Localization Accuracy: 10.8. Result ID: 69a184e435dfcabb00e790fa.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

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

Recorded evaluation configuration: {"Zoom Depth":"d2"}. This record does not assert independent reproduction.

### UI-TARS-7B

Localization Accuracy: 10.8. Result ID: 69a184e435dfcabb00e790fe.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a61e209131cea6e2ba.md>)

Recorded evaluation configuration: {"Zoom Depth":"d2"}. This record does not assert independent reproduction.

### Claude-4.5-Sonnet

Localization Accuracy: 10.5. Result ID: 69a184e435dfcabb00e790f0.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d1"}. This record does not assert independent reproduction.

### GPT-5

Localization Accuracy: 8.1. Result ID: 69a184e435dfcabb00e790ed.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d2"}. This record does not assert independent reproduction.

### GPT-5

Localization Accuracy: 5.4. Result ID: 69a184e435dfcabb00e790ef.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d4"}. This record does not assert independent reproduction.

### UI-TARS-7B

Localization Accuracy: 5.4. Result ID: 69a184e435dfcabb00e790fd.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a61e209131cea6e2ba.md>)

Recorded evaluation configuration: {"Zoom Depth":"d1"}. This record does not assert independent reproduction.

### GPT-5

Localization Accuracy: 2.7. Result ID: 69a184e435dfcabb00e790ee.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d3"}. This record does not assert independent reproduction.

### GPT-5

Localization Accuracy: 0. Result ID: 69a184e435dfcabb00e790ec.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

Recorded evaluation configuration: {"Zoom Depth":"d1"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Localization Accuracy: 0. Result ID: 69a184e435dfcabb00e790f9.

[Reporting paper](<https://www.sota2.com/research/paper/69365b83d6b0dd3342934c20.md>)

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

Recorded evaluation configuration: {"Zoom Depth":"d1"}. This record does not assert independent reproduction.

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