# Image Editing on Editing

Source: [Image Editing on Editing](<https://www.sota2.com/research/sota/image-editing-on-editing>)

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

Data updated: 2026-05-08T08:37:26.323Z

Evaluation of Image Editing performance on the Editing dataset, reporting scores for Background (Bkg.) and Overall performance.

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 | Image Editing |
| Dataset (including any stated split) | Editing |
| Metric | Bkg. Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Bkg. Score](<https://www.sota2.com/research/sota/image-editing-on-editing.md?metric=Bkg.%20Score>): Higher is better; unit: SCALAR.

- [Overall Score](<https://www.sota2.com/research/sota/image-editing-on-editing.md?metric=Overall%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Bkg. Score | Result date | Report paper |
| --- | --- | --- | --- |
| MUSE-3B | 4.22 | Not recorded | 69fd6e365497b3b670c89518 |
| UniLIP-3B | 4.14 | Not recorded | 69fd6e365497b3b670c89518 |
| MUSE-1B | 4.12 | Not recorded | 69fd6e365497b3b670c89518 |
| UniLIP-1B | 4 | Not recorded | 69fd6e365497b3b670c89518 |
| OmniGen2 | 3.57 | Not recorded | 69fd6e365497b3b670c89518 |
| BAGEL | 3.24 | Not recorded | 69fd6e365497b3b670c89518 |

### MUSE-3B

Bkg. Score: 4.22. Result ID: 69fda05247f34ce924e0a224.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e365497b3b670c89518.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e365497b3b670c89518.md>)

Recorded evaluation configuration: {"Type":"Unified","# Params":"2B+1.6B"}. This record does not assert independent reproduction.

### UniLIP-3B

Bkg. Score: 4.14. Result ID: 69fda05247f34ce924e0a223.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e365497b3b670c89518.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba72.md>)

Recorded evaluation configuration: {"Type":"Unified","# Params":"2B+1.6B"}. This record does not assert independent reproduction.

### MUSE-1B

Bkg. Score: 4.12. Result ID: 69fda05247f34ce924e0a222.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e365497b3b670c89518.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e365497b3b670c89518.md>)

Recorded evaluation configuration: {"Type":"Unified","# Params":"1B+0.6B"}. This record does not assert independent reproduction.

### UniLIP-1B

Bkg. Score: 4. Result ID: 69fda05247f34ce924e0a221.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e365497b3b670c89518.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba72.md>)

Recorded evaluation configuration: {"Type":"Unified","# Params":"1B+0.6B"}. This record does not assert independent reproduction.

### OmniGen2

Bkg. Score: 3.57. Result ID: 69fda05247f34ce924e0a220.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e365497b3b670c89518.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba31e209131cea89864.md>)

Recorded evaluation configuration: {"Type":"Dual","# Params":"3B+4B"}. This record does not assert independent reproduction.

### BAGEL

Bkg. Score: 3.24. Result ID: 69fda05247f34ce924e0a21f.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e365497b3b670c89518.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a311e209131cea81aad.md>)

[Implementation](<https://bagel-ai.org/>)

Recorded evaluation configuration: {"Type":"Dual","# Params":"3B"}. This record does not assert independent reproduction.

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