# Image Editing on VCR-Bench Img2mg

Source: [Image Editing on VCR-Bench Img2mg](<https://www.sota2.com/research/sota/image-editing-on-vcr-bench-img2mg>)

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

Data updated: 2026-03-11T06:52:28.620Z

Evaluation of image editing performance on the VCR-Bench Img2mg dataset, typically measured using a general performance score.

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) | VCR-Bench Img2mg |
| Metric | Performance Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Performance Score](<https://www.sota2.com/research/sota/image-editing-on-vcr-bench-img2mg.md?metric=Performance%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Performance Score | Result date | Report paper |
| --- | --- | --- | --- |
| VC-R1 vs. Gemini | 5.8 | Not recorded | 69b0f6e92d603e6de3e45b88 |
| VisionCreator-R1 | 0.836 | Not recorded | 69b0f6e92d603e6de3e45b88 |
| Gemini2.5Pro | 0.816 | Not recorded | 69b0f6e92d603e6de3e45b88 |
| Qwen3VL32B | 0.806 | Not recorded | 69b0f6e92d603e6de3e45b88 |
| Qwen-Image-Fast | 0.672 | Not recorded | 69b0f6e92d603e6de3e45b88 |

### VC-R1 vs. Gemini

Performance Score: 5.8. Result ID: 69b110316dbb7075b95ad648.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6e92d603e6de3e45b88.md>)

Recorded evaluation configuration: {"Evaluator":"Human"}. This record does not assert independent reproduction.

### VisionCreator-R1

Performance Score: 0.836. Result ID: 69b110316dbb7075b95ad647.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6e92d603e6de3e45b88.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6e92d603e6de3e45b88.md>)

Recorded evaluation configuration: {"Evaluator":"Gemini2.5Pro"}. This record does not assert independent reproduction.

### Gemini2.5Pro

Performance Score: 0.816. Result ID: 69b110316dbb7075b95ad646.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6e92d603e6de3e45b88.md>)

Recorded evaluation configuration: {"Evaluator":"Gemini2.5Pro"}. This record does not assert independent reproduction.

### Qwen3VL32B

Performance Score: 0.806. Result ID: 69b110316dbb7075b95ad645.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6e92d603e6de3e45b88.md>)

Recorded evaluation configuration: {"Evaluator":"Gemini2.5Pro"}. This record does not assert independent reproduction.

### Qwen-Image-Fast

Performance Score: 0.672. Result ID: 69b110316dbb7075b95ad644.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6e92d603e6de3e45b88.md>)

Recorded evaluation configuration: {"Evaluator":"Gemini2.5Pro"}. This record does not assert independent reproduction.

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