# Image Generation and Editing on VPTT Human Study (6000 annotations) (test)

Source: [Image Generation and Editing on VPTT Human Study (6000 annotations) (test)](<https://www.sota2.com/research/sota/image-generation-and-editing-on-vptt-human-study-6000-annotations-test>)

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

Data updated: 2026-02-26T06:08:03.330Z

Evaluation of Image Generation and Editing models using the VPTT Human Study dataset (6000 annotations, test split), incorporating VPTTscore, VLM, and human perceptual metrics.

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 Generation and Editing |
| Dataset (including any stated split) | VPTT Human Study (6000 annotations) (test) |
| Metric | VPTTscore-c (Text) Avg |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [VPTTscore-c (Text) Avg](<https://www.sota2.com/research/sota/image-generation-and-editing-on-vptt-human-study-6000-annotations-test.md?metric=VPTTscore-c%20(Text)%20Avg>): Higher is better; unit: SCALAR.

- [VPTTscore-c (Text) Acc](<https://www.sota2.com/research/sota/image-generation-and-editing-on-vptt-human-study-6000-annotations-test.md?metric=VPTTscore-c%20(Text)%20Acc>): Higher is better; unit: PERCENT.

- [VLM (Visual) Avg](<https://www.sota2.com/research/sota/image-generation-and-editing-on-vptt-human-study-6000-annotations-test.md?metric=VLM%20(Visual)%20Avg>): Higher is better; unit: SCALAR.

- [VLM (Visual) Acc](<https://www.sota2.com/research/sota/image-generation-and-editing-on-vptt-human-study-6000-annotations-test.md?metric=VLM%20(Visual)%20Acc>): Higher is better; unit: PERCENT.

- [Human (Perceptual) Avg](<https://www.sota2.com/research/sota/image-generation-and-editing-on-vptt-human-study-6000-annotations-test.md?metric=Human%20(Perceptual)%20Avg>): Higher is better; unit: SCALAR.

- [Human (Perceptual) Acc](<https://www.sota2.com/research/sota/image-generation-and-editing-on-vptt-human-study-6000-annotations-test.md?metric=Human%20(Perceptual)%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | VPTTscore-c (Text) Avg | Result date | Report paper |
| --- | --- | --- | --- |
| VPRAG | 0.464 | Not recorded | 69802f6ca8b01e76cc8e14fb |
| BRAG | 0.42 | Not recorded | 69802f6ca8b01e76cc8e14fb |
| Persona Only | 0.4 | Not recorded | 69802f6ca8b01e76cc8e14fb |
| Baseline | 0.329 | Not recorded | 69802f6ca8b01e76cc8e14fb |

### VPRAG

VPTTscore-c (Text) Avg: 0.464. Result ID: 6997729e5698665ec4c6ad82.

[Reporting paper](<https://www.sota2.com/research/paper/69802f6ca8b01e76cc8e14fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802f6ca8b01e76cc8e14fb.md>)

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

### BRAG

VPTTscore-c (Text) Avg: 0.42. Result ID: 6997729e5698665ec4c6ad81.

[Reporting paper](<https://www.sota2.com/research/paper/69802f6ca8b01e76cc8e14fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa766a1e209131cea6ccd9.md>)

[Implementation](<https://github.com/zzjchen/Tailored-Visions>)

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

### Persona Only

VPTTscore-c (Text) Avg: 0.4. Result ID: 6997729e5698665ec4c6ad80.

[Reporting paper](<https://www.sota2.com/research/paper/69802f6ca8b01e76cc8e14fb.md>)

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

### Baseline

VPTTscore-c (Text) Avg: 0.329. Result ID: 6997729e5698665ec4c6ad7f.

[Reporting paper](<https://www.sota2.com/research/paper/69802f6ca8b01e76cc8e14fb.md>)

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

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