# GUI Navigation on GUI-Odyssey High

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

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

Data updated: 2026-02-26T05:34:39.555Z

Evaluation of agent performance on GUI Navigation tasks using the GUI-Odyssey High dataset, focusing on interaction success and action matching.

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 Navigation |
| Dataset (including any stated split) | GUI-Odyssey High |
| Metric | Action Matching Score (AMS) |
| 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

- [Action Matching Score (AMS)](<https://www.sota2.com/research/sota/gui-navigation-on-gui-odyssey-high.md?metric=Action%20Matching%20Score%20(AMS)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Action Matching Score (AMS) | Result date | Report paper |
| --- | --- | --- | --- |
| SpiritSight-8B | 75.8 | Not recorded | 68fa78041e209131cea765a6 |
| OdysseyAgent | 74.3 | Not recorded | 68fa78041e209131cea765a6 |
| SpiritSight-2B | 72.3 | Not recorded | 68fa78041e209131cea765a6 |
| GPT-4o | 20.4 | Not recorded | 68fa78041e209131cea765a6 |

### SpiritSight-8B

Action Matching Score (AMS): 75.8. Result ID: 6995786c3badfaffe66f0cba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78041e209131cea765a6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78041e209131cea765a6.md>)

[Implementation](<https://hzhiyuan.github.io/SpiritSight-Agent>)

Recorded evaluation configuration: {"Model Size":"8B"}. This record does not assert independent reproduction.

### OdysseyAgent

Action Matching Score (AMS): 74.3. Result ID: 6995786c3badfaffe66f0cb8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78041e209131cea765a6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a561e209131cea8291d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SpiritSight-2B

Action Matching Score (AMS): 72.3. Result ID: 6995786c3badfaffe66f0cb9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78041e209131cea765a6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78041e209131cea765a6.md>)

[Implementation](<https://hzhiyuan.github.io/SpiritSight-Agent>)

Recorded evaluation configuration: {"Model Size":"2B"}. This record does not assert independent reproduction.

### GPT-4o

Action Matching Score (AMS): 20.4. Result ID: 6995786c3badfaffe66f0cb7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78041e209131cea765a6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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