# Image Editing on ImgEdit Benchmark 2025 (full)

Source: [Image Editing on ImgEdit Benchmark 2025 (full)](<https://www.sota2.com/research/sota/image-editing-on-imgedit-benchmark-2025-full>)

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

Data updated: 2026-03-17T07:20:00.409Z

Evaluation of image editing performance on the ImgEdit Benchmark 2025 (full) dataset, reporting scores across ten specific operational dimensions: Add, Adjust, Extract, Replace, Remove, Background, Style, Hybrid, Action, and Overall.

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) | ImgEdit Benchmark 2025 (full) |
| Metric | Add Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Add Score](<https://www.sota2.com/research/sota/image-editing-on-imgedit-benchmark-2025-full.md?metric=Add%20Score>): Higher is better; unit: SCALAR.

- [Adjust Score](<https://www.sota2.com/research/sota/image-editing-on-imgedit-benchmark-2025-full.md?metric=Adjust%20Score>): Higher is better; unit: SCALAR.

- [Extract Score](<https://www.sota2.com/research/sota/image-editing-on-imgedit-benchmark-2025-full.md?metric=Extract%20Score>): Higher is better; unit: SCALAR.

- [Replace Score](<https://www.sota2.com/research/sota/image-editing-on-imgedit-benchmark-2025-full.md?metric=Replace%20Score>): Higher is better; unit: SCALAR.

- [Remove Score](<https://www.sota2.com/research/sota/image-editing-on-imgedit-benchmark-2025-full.md?metric=Remove%20Score>): Higher is better; unit: SCALAR.

- [Background Score](<https://www.sota2.com/research/sota/image-editing-on-imgedit-benchmark-2025-full.md?metric=Background%20Score>): Higher is better; unit: SCALAR.

- [Style Score](<https://www.sota2.com/research/sota/image-editing-on-imgedit-benchmark-2025-full.md?metric=Style%20Score>): Higher is better; unit: SCALAR.

- [Hybrid Score](<https://www.sota2.com/research/sota/image-editing-on-imgedit-benchmark-2025-full.md?metric=Hybrid%20Score>): Higher is better; unit: SCALAR.

- [Action Score](<https://www.sota2.com/research/sota/image-editing-on-imgedit-benchmark-2025-full.md?metric=Action%20Score>): Higher is better; unit: SCALAR.

- [Overall Score](<https://www.sota2.com/research/sota/image-editing-on-imgedit-benchmark-2025-full.md?metric=Overall%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Add Score | Result date | Report paper |
| --- | --- | --- | --- |
| MoS-Image-L | 4.63 | Not recorded | 691bfd7d6750be83fe5ce790 |
| GPT Image 1 \[High\] | 4.61 | Not recorded | 691bfd7d6750be83fe5ce790 |
| MoS-Image-S | 4.4 | Not recorded | 691bfd7d6750be83fe5ce790 |
| Qwen-Image | 4.38 | Not recorded | 691bfd7d6750be83fe5ce790 |
| FLUX.1 Kontext \[Pro\] | 4.25 | Not recorded | 691bfd7d6750be83fe5ce790 |
| Step1X-Edit | 3.88 | Not recorded | 691bfd7d6750be83fe5ce790 |
| UniWorld-V1 | 3.82 | Not recorded | 691bfd7d6750be83fe5ce790 |
| ICEdit | 3.58 | Not recorded | 691bfd7d6750be83fe5ce790 |
| OmniGen2 | 3.57 | Not recorded | 691bfd7d6750be83fe5ce790 |
| BAGEL | 3.56 | Not recorded | 691bfd7d6750be83fe5ce790 |
| OmniGen | 3.47 | Not recorded | 691bfd7d6750be83fe5ce790 |
| UltraEdit | 3.44 | Not recorded | 691bfd7d6750be83fe5ce790 |
| AnyEdit | 3.18 | Not recorded | 691bfd7d6750be83fe5ce790 |
| MagicBrush | 2.84 | Not recorded | 691bfd7d6750be83fe5ce790 |
| Instruct-Pix2Pix | 2.45 | Not recorded | 691bfd7d6750be83fe5ce790 |

### MoS-Image-L

Add Score: 4.63. Result ID: 69b9009a47f34ce924a10f8c.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

Recorded evaluation configuration: {"#Param":"5B"}. This record does not assert independent reproduction.

### GPT Image 1 \[High\]

Add Score: 4.61. Result ID: 69b9009a47f34ce924a10f7f.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

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

### MoS-Image-S

Add Score: 4.4. Result ID: 69b9009a47f34ce924a10f8b.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

Recorded evaluation configuration: {"#Param":"3B"}. This record does not assert independent reproduction.

### Qwen-Image

Add Score: 4.38. Result ID: 69b9009a47f34ce924a10f80.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a6a1e209131cea83137.md>)

Recorded evaluation configuration: {"#Param":"20B"}. This record does not assert independent reproduction.

### FLUX.1 Kontext \[Pro\]

Add Score: 4.25. Result ID: 69b9009a47f34ce924a10f7e.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79a81e209131cea7eb79.md>)

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

### Step1X-Edit

Add Score: 3.88. Result ID: 69b9009a47f34ce924a10f87.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a551e209131cea82892.md>)

[Implementation](<https://github.com/stepfun-ai/Step1X-Edit>)

Recorded evaluation configuration: {"#Param":"12B"}. This record does not assert independent reproduction.

### UniWorld-V1

Add Score: 3.82. Result ID: 69b9009a47f34ce924a10f89.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79831e209131cea7dee8.md>)

Recorded evaluation configuration: {"#Param":"12B"}. This record does not assert independent reproduction.

### ICEdit

Add Score: 3.58. Result ID: 69b9009a47f34ce924a10f86.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b8a1e209131cea89042.md>)

Recorded evaluation configuration: {"#Param":"0.2B"}. This record does not assert independent reproduction.

### OmniGen2

Add Score: 3.57. Result ID: 69b9009a47f34ce924a10f8a.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

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

Recorded evaluation configuration: {"#Param":"4B"}. This record does not assert independent reproduction.

### BAGEL

Add Score: 3.56. Result ID: 69b9009a47f34ce924a10f88.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

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

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

Recorded evaluation configuration: {"#Param":"14B"}. This record does not assert independent reproduction.

### OmniGen

Add Score: 3.47. Result ID: 69b9009a47f34ce924a10f85.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d81e209131cea6a322.md>)

Recorded evaluation configuration: {"#Param":"3.8B"}. This record does not assert independent reproduction.

### UltraEdit

Add Score: 3.44. Result ID: 69b9009a47f34ce924a10f84.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76461e209131cea6c155.md>)

[Implementation](<https://www.sota2.com/ultra-editing.github.io>)

Recorded evaluation configuration: {"#Param":"2.5B"}. This record does not assert independent reproduction.

### AnyEdit

Add Score: 3.18. Result ID: 69b9009a47f34ce924a10f83.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b91e209131cea74f9f.md>)

[Implementation](<https://dcd-anyedit.github.io/>)

Recorded evaluation configuration: {"#Param":"0.86B"}. This record does not assert independent reproduction.

### MagicBrush

Add Score: 2.84. Result ID: 69b9009a47f34ce924a10f81.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa732e1e209131cea5af49.md>)

[Implementation](<https://osu-nlp-group.github.io/MagicBrush>)

Recorded evaluation configuration: {"#Param":"0.86B"}. This record does not assert independent reproduction.

### Instruct-Pix2Pix

Add Score: 2.45. Result ID: 69b9009a47f34ce924a10f82.

[Reporting paper](<https://www.sota2.com/research/paper/691bfd7d6750be83fe5ce790.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e641e209131cea3fa43.md>)

[Implementation](<https://www.sota2.com/timothybrooks.com/instruct-pix2pix>)

Recorded evaluation configuration: {"#Param":"0.86B"}. This record does not assert independent reproduction.

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