# GUI Agent Navigation on GUI-Odyssey (test)

Source: [GUI Agent Navigation on GUI-Odyssey (test)](<https://www.sota2.com/research/sota/gui-agent-navigation-on-gui-odyssey-test>)

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

Data updated: 2026-03-06T09:08:52.971Z

Evaluation of GUI Agent Navigation performance on the test split of the GUI-Odyssey dataset, reporting Type accuracy, Grounding Rate (GR), and Success Rate (SR).

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 Agent Navigation |
| Dataset (including any stated split) | GUI-Odyssey (test) |
| Metric | Type Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Type Accuracy](<https://www.sota2.com/research/sota/gui-agent-navigation-on-gui-odyssey-test.md?metric=Type%20Accuracy>): Higher is better; unit: PERCENT.

- [Grounding Rate (GR)](<https://www.sota2.com/research/sota/gui-agent-navigation-on-gui-odyssey-test.md?metric=Grounding%20Rate%20(GR)>): Higher is better; unit: PERCENT.

- [Success Rate (SR)](<https://www.sota2.com/research/sota/gui-agent-navigation-on-gui-odyssey-test.md?metric=Success%20Rate%20(SR)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Type Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| WebFactory-3B | 66 | Not recorded | 69aa5f8d2d603e6de3e418cf |
| GUI-R1-3B | 54.8 | Not recorded | 69aa5f8d2d603e6de3e418cf |
| QwenVL2.5-3B | 38.4 | Not recorded | 69aa5f8d2d603e6de3e418cf |
| GPT-4o | 37.5 | Not recorded | 69aa5f8d2d603e6de3e418cf |

### WebFactory-3B

Type Accuracy: 66. Result ID: 69aa994a6dbb7075b95487f8.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8d2d603e6de3e418cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69aa5f8d2d603e6de3e418cf.md>)

Recorded evaluation configuration: {"Setting":"RL Fine-Tuning"}. This record does not assert independent reproduction.

### GUI-R1-3B

Type Accuracy: 54.8. Result ID: 69aa994a6dbb7075b95487f7.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8d2d603e6de3e418cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bbf1e209131cea8a2a0.md>)

Recorded evaluation configuration: {"Setting":"RL Fine-Tuning"}. This record does not assert independent reproduction.

### QwenVL2.5-3B

Type Accuracy: 38.4. Result ID: 69aa994a6dbb7075b95487f6.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8d2d603e6de3e418cf.md>)

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

Recorded evaluation configuration: {"Setting":"Zero-Shot"}. This record does not assert independent reproduction.

### GPT-4o

Type Accuracy: 37.5. Result ID: 69aa994a6dbb7075b95487f5.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f8d2d603e6de3e418cf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: {"Setting":"Zero-Shot"}. This record does not assert independent reproduction.

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