# Mobile Use Navigation on GUI Odyssey static offline benchmark

Source: [Mobile Use Navigation on GUI Odyssey static offline benchmark](<https://www.sota2.com/research/sota/mobile-use-navigation-on-gui-odyssey-static-offline-benchmark>)

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

Data updated: 2026-02-26T06:05:12.282Z

Evaluation of mobile agent navigation performance on the static offline version of the GUI Odyssey benchmark.

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 | Mobile Use Navigation |
| Dataset (including any stated split) | GUI Odyssey static offline benchmark |
| Metric | Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

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

## Recorded results

| Method | Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| MAI-UI-32B | 83.4 | Not recorded | 69520ae053fdd5c36173d429 |
| MAI-UI-8B | 80.1 | Not recorded | 69520ae053fdd5c36173d429 |
| OS-Atlas-7B | 76.8 | Not recorded | 69520ae053fdd5c36173d429 |
| AgentCPM-GUI-8B | 75 | Not recorded | 69520ae053fdd5c36173d429 |
| OdysseyAgent-7B | 73.7 | Not recorded | 69520ae053fdd5c36173d429 |
| MAI-UI-2B | 72.6 | Not recorded | 69520ae053fdd5c36173d429 |
| UI-Venus-72B | 72.4 | Not recorded | 69520ae053fdd5c36173d429 |
| UI-TARS-7B | 67.9 | Not recorded | 69520ae053fdd5c36173d429 |
| Aguvis-7B | 13.5 | Not recorded | 69520ae053fdd5c36173d429 |

### MAI-UI-32B

Success Rate: 83.4. Result ID: 6998094d5698665ec462dc3d.

[Reporting paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

Recorded evaluation configuration: {"Parameters":"32B"}. This record does not assert independent reproduction.

### MAI-UI-8B

Success Rate: 80.1. Result ID: 6998094d5698665ec462dc3c.

[Reporting paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

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

### OS-Atlas-7B

Success Rate: 76.8. Result ID: 6998094d5698665ec462dc37.

[Reporting paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75791e209131cea68351.md>)

[Implementation](<https://osatlas.github.io/>)

Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction.

### AgentCPM-GUI-8B

Success Rate: 75. Result ID: 6998094d5698665ec462dc35.

[Reporting paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79861e209131cea7e031.md>)

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

### OdysseyAgent-7B

Success Rate: 73.7. Result ID: 6998094d5698665ec462dc39.

[Reporting paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

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

Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction.

### MAI-UI-2B

Success Rate: 72.6. Result ID: 6998094d5698665ec462dc3b.

[Reporting paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

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

### UI-Venus-72B

Success Rate: 72.4. Result ID: 6998094d5698665ec462dc3a.

[Reporting paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea849f9.md>)

Recorded evaluation configuration: {"Parameters":"72B"}. This record does not assert independent reproduction.

### UI-TARS-7B

Success Rate: 67.9. Result ID: 6998094d5698665ec462dc36.

[Reporting paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

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

Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction.

### Aguvis-7B

Success Rate: 13.5. Result ID: 6998094d5698665ec462dc38.

[Reporting paper](<https://www.sota2.com/research/paper/69520ae053fdd5c36173d429.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78581e209131cea77d9c.md>)

Recorded evaluation configuration: {"Parameters":"7B"}. This record does not assert independent reproduction.

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