# GUI Visual Grounding on ScreenSpot Agent Setting Standard

Source: [GUI Visual Grounding on ScreenSpot Agent Setting Standard](<https://www.sota2.com/research/sota/gui-visual-grounding-on-screenspot-agent-setting-standard>)

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

Data updated: 2026-02-26T05:52:54.750Z

Evaluation of GUI Visual Grounding performance on the ScreenSpot Agent Setting Standard dataset, reporting platform-specific accuracy (Mobile, Desktop, Web) for text and icon/widget grounding.

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 Visual Grounding |
| Dataset (including any stated split) | ScreenSpot Agent Setting Standard |
| Metric | Mobile Text Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Mobile Text Acc](<https://www.sota2.com/research/sota/gui-visual-grounding-on-screenspot-agent-setting-standard.md?metric=Mobile%20Text%20Acc>): Higher is better; unit: PERCENT.

- [Mobile Icon/Widget Acc](<https://www.sota2.com/research/sota/gui-visual-grounding-on-screenspot-agent-setting-standard.md?metric=Mobile%20Icon%2FWidget%20Acc>): Higher is better; unit: PERCENT.

- [Desktop Text Acc](<https://www.sota2.com/research/sota/gui-visual-grounding-on-screenspot-agent-setting-standard.md?metric=Desktop%20Text%20Acc>): Higher is better; unit: PERCENT.

- [Desktop Icon/Widget Acc](<https://www.sota2.com/research/sota/gui-visual-grounding-on-screenspot-agent-setting-standard.md?metric=Desktop%20Icon%2FWidget%20Acc>): Higher is better; unit: PERCENT.

- [Web Text Acc](<https://www.sota2.com/research/sota/gui-visual-grounding-on-screenspot-agent-setting-standard.md?metric=Web%20Text%20Acc>): Higher is better; unit: PERCENT.

- [Web Icon/Widget Acc](<https://www.sota2.com/research/sota/gui-visual-grounding-on-screenspot-agent-setting-standard.md?metric=Web%20Icon%2FWidget%20Acc>): Higher is better; unit: PERCENT.

- [Average Acc](<https://www.sota2.com/research/sota/gui-visual-grounding-on-screenspot-agent-setting-standard.md?metric=Average%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Mobile Text Acc | Result date | Report paper |
| --- | --- | --- | --- |
| UGround-V1-72B | 94.5 | Not recorded | 68fa79851e209131cea7dfab |
| UGround-V1-2B | 94.1 | Not recorded | 68fa79851e209131cea7dfab |
| UGround-V1-7B | 94.1 | Not recorded | 68fa79851e209131cea7dfab |
| UGround | 93.4 | Not recorded | 68fa79851e209131cea7dfab |
| UGround | 90.1 | Not recorded | 68fa79851e209131cea7dfab |
| SeeClick | 81 | Not recorded | 68fa79851e209131cea7dfab |
| SeeClick | 76.6 | Not recorded | 68fa79851e209131cea7dfab |

### UGround-V1-72B

Mobile Text Acc: 94.5. Result ID: 698b51ee8d67a41d0a6d0f2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Implementation](<https://osu-nlp-group.github.io/UGround/>)

Recorded evaluation configuration: {"Planner":"GPT-4o"}. This record does not assert independent reproduction.

### UGround-V1-2B

Mobile Text Acc: 94.1. Result ID: 698b51ee8d67a41d0a6d0f29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Implementation](<https://osu-nlp-group.github.io/UGround/>)

Recorded evaluation configuration: {"Planner":"GPT-4o"}. This record does not assert independent reproduction.

### UGround-V1-7B

Mobile Text Acc: 94.1. Result ID: 698b51ee8d67a41d0a6d0f2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Implementation](<https://osu-nlp-group.github.io/UGround/>)

Recorded evaluation configuration: {"Planner":"GPT-4o"}. This record does not assert independent reproduction.

### UGround

Mobile Text Acc: 93.4. Result ID: 698b51ee8d67a41d0a6d0f28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Implementation](<https://osu-nlp-group.github.io/UGround/>)

Recorded evaluation configuration: {"Planner":"GPT-4o"}. This record does not assert independent reproduction.

### UGround

Mobile Text Acc: 90.1. Result ID: 698b51ee8d67a41d0a6d0f26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Implementation](<https://osu-nlp-group.github.io/UGround/>)

Recorded evaluation configuration: {"Planner":"GPT-4"}. This record does not assert independent reproduction.

### SeeClick

Mobile Text Acc: 81. Result ID: 698b51ee8d67a41d0a6d0f27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72441e209131cea55627.md>)

[Implementation](<https://github.com/njucckevin/SeeClick>)

Recorded evaluation configuration: {"Planner":"GPT-4o"}. This record does not assert independent reproduction.

### SeeClick

Mobile Text Acc: 76.6. Result ID: 698b51ee8d67a41d0a6d0f25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79851e209131cea7dfab.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72441e209131cea55627.md>)

[Implementation](<https://github.com/njucckevin/SeeClick>)

Recorded evaluation configuration: {"Planner":"GPT-4"}. This record does not assert independent reproduction.

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