# Pairwise preference prediction on HPD v3++ v1 (test)

Source: [Pairwise preference prediction on HPD v3++ v1 (test)](<https://www.sota2.com/research/sota/pairwise-preference-prediction-on-hpd-v3-plus-plus-v1-test>)

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

Data updated: 2026-06-15T08:02:30.861Z

Evaluation of model performance on the test split of the HPD v3++ v1 dataset for pairwise preference prediction.

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 | Pairwise preference prediction |
| Dataset (including any stated split) | HPD v3++ v1 (test) |
| Metric | Aesthetic Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Aesthetic Score](<https://www.sota2.com/research/sota/pairwise-preference-prediction-on-hpd-v3-plus-plus-v1-test.md?metric=Aesthetic%20Score>): Higher is better; unit: SCALAR.

- [Temporal Following Score](<https://www.sota2.com/research/sota/pairwise-preference-prediction-on-hpd-v3-plus-plus-v1-test.md?metric=Temporal%20Following%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Aesthetic Score | Result date | Report paper |
| --- | --- | --- | --- |
| HPSv3++ | 79.1 | Not recorded | 6a2f873cd33dfb23e783c1ad |
| HPSv3 | 74.8 | Not recorded | 6a2f873cd33dfb23e783c1ad |
| ImageReward | 58.5 | Not recorded | 6a2f873cd33dfb23e783c1ad |
| PickScore | 57.9 | Not recorded | 6a2f873cd33dfb23e783c1ad |
| UnifiedReward | 57.9 | Not recorded | 6a2f873cd33dfb23e783c1ad |
| Aesthetic Score | 56.1 | Not recorded | 6a2f873cd33dfb23e783c1ad |
| CLIP ViT-H/14 | 51.8 | Not recorded | 6a2f873cd33dfb23e783c1ad |

### HPSv3++

Aesthetic Score: 79.1. Result ID: 6a2fb17cfbc373592c2bdc24.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f873cd33dfb23e783c1ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2f873cd33dfb23e783c1ad.md>)

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

### HPSv3

Aesthetic Score: 74.8. Result ID: 6a2fb17cfbc373592c2bdc23.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f873cd33dfb23e783c1ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ad71e209131cea85763.md>)

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

### ImageReward

Aesthetic Score: 58.5. Result ID: 6a2fb17cfbc373592c2bdc20.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f873cd33dfb23e783c1ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa719f1e209131cea52222.md>)

[Implementation](<https://github.com/THUDM/ImageReward>)

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

### PickScore

Aesthetic Score: 57.9. Result ID: 6a2fb17cfbc373592c2bdc21.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f873cd33dfb23e783c1ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713e1e209131cea500c1.md>)

[Implementation](<https://github.com/yuvalkirstain/PickScore>)

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

### UnifiedReward

Aesthetic Score: 57.9. Result ID: 6a2fb17cfbc373592c2bdc22.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f873cd33dfb23e783c1ad.md>)

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

### Aesthetic Score

Aesthetic Score: 56.1. Result ID: 6a2fb17cfbc373592c2bdc1f.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f873cd33dfb23e783c1ad.md>)

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

### CLIP ViT-H/14

Aesthetic Score: 51.8. Result ID: 6a2fb17cfbc373592c2bdc1e.

[Reporting paper](<https://www.sota2.com/research/paper/6a2f873cd33dfb23e783c1ad.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0f1e209131cea31cc9.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.