# Action Sequence Generation on OmniACT (test)

Source: [Action Sequence Generation on OmniACT (test)](<https://www.sota2.com/research/sota/action-sequence-generation-on-omniact-test>)

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

Data updated: 2026-02-26T05:34:39.772Z

Evaluation of model performance on generating action sequences using the test split of the OmniACT dataset.

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 | Action Sequence Generation |
| Dataset (including any stated split) | OmniACT (test) |
| Metric | Action Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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 Score](<https://www.sota2.com/research/sota/action-sequence-generation-on-omniact-test.md?metric=Action%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Action Score | Result date | Report paper |
| --- | --- | --- | --- |
| UGround-V1-7B | 34 | Not recorded | 68fa79851e209131cea7dfab |
| UGround-V1-2B | 32.9 | Not recorded | 68fa79851e209131cea7dfab |
| UGround | 32.8 | Not recorded | 68fa79851e209131cea7dfab |
| UGround | 31.1 | Not recorded | 68fa79851e209131cea7dfab |
| SeeClick | 29.6 | Not recorded | 68fa79851e209131cea7dfab |
| SeeClick | 28.9 | Not recorded | 68fa79851e209131cea7dfab |
| DetACT | 17 | Not recorded | 68fa79851e209131cea7dfab |
| DetACT | 11.6 | Not recorded | 68fa79851e209131cea7dfab |

### UGround-V1-7B

Action Score: 34. Result ID: 698b51ee8d67a41d0a6d0f63.

[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: {"Inputs":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction.

### UGround-V1-2B

Action Score: 32.9. Result ID: 698b51ee8d67a41d0a6d0f62.

[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: {"Inputs":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction.

### UGround

Action Score: 32.8. Result ID: 698b51ee8d67a41d0a6d0f61.

[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: {"Inputs":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction.

### UGround

Action Score: 31.1. Result ID: 698b51ee8d67a41d0a6d0f5f.

[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: {"Inputs":"Image (SeeAct-V)","Planner":"GPT-4"}. This record does not assert independent reproduction.

### SeeClick

Action Score: 29.6. Result ID: 698b51ee8d67a41d0a6d0f60.

[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: {"Inputs":"Image (SeeAct-V)","Planner":"GPT-4o"}. This record does not assert independent reproduction.

### SeeClick

Action Score: 28.9. Result ID: 698b51ee8d67a41d0a6d0f5e.

[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: {"Inputs":"Image (SeeAct-V)","Planner":"GPT-4"}. This record does not assert independent reproduction.

### DetACT

Action Score: 17. Result ID: 698b51ee8d67a41d0a6d0f5d.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa74361e209131cea60759.md>)

Recorded evaluation configuration: {"Inputs":"Image + Text","Planner":"GPT-4"}. This record does not assert independent reproduction.

### DetACT

Action Score: 11.6. Result ID: 698b51ee8d67a41d0a6d0f5c.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa74361e209131cea60759.md>)

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

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