# Discrimination on Photorealistic discrimination dataset (test)

Source: [Discrimination on Photorealistic discrimination dataset (test)](<https://www.sota2.com/research/sota/discrimination-on-photorealistic-discrimination-dataset-test>)

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

Data updated: 2026-02-26T06:01:09.935Z

Evaluation of model performance on the Discrimination task using the test split of the Photorealistic discrimination dataset.

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 | Discrimination |
| Dataset (including any stated split) | Photorealistic discrimination dataset (test) |
| Metric | Realistic Acc |
| Unit | PERCENT |
| 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

- [Realistic Acc](<https://www.sota2.com/research/sota/discrimination-on-photorealistic-discrimination-dataset-test.md?metric=Realistic%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Realistic Acc | Result date | Report paper |
| --- | --- | --- | --- |
| CLIP | 93.9 | Not recorded | 68fa75d11e209131cea6a00d |
| ImageNet | 53 | Not recorded | 68fa75d11e209131cea6a00d |
| MAE | 52.4 | Not recorded | 68fa75d11e209131cea6a00d |
| DINO | 50.9 | Not recorded | 68fa75d11e209131cea6a00d |
| ViT-B/16 (No pre-training) | 49.9 | Not recorded | 68fa75d11e209131cea6a00d |
| DINOv2 | 48 | Not recorded | 68fa75d11e209131cea6a00d |

### CLIP

Realistic Acc: 93.9. Result ID: 6993fda23a6c3148491a2188.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pretraining Scale":"400M","Zero-shot evaluation":true}. This record does not assert independent reproduction.

### ImageNet

Realistic Acc: 53. Result ID: 6993fda23a6c3148491a218a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pretraining Scale":"14.2M","Zero-shot evaluation":true}. This record does not assert independent reproduction.

### MAE

Realistic Acc: 52.4. Result ID: 6993fda23a6c3148491a218c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7f1e209131cea2e973.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pretraining Scale":"1.28M","Zero-shot evaluation":true}. This record does not assert independent reproduction.

### DINO

Realistic Acc: 50.9. Result ID: 6993fda23a6c3148491a218b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea2594c.md>)

[Implementation](<https://github.com/facebookresearch/dino>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pretraining Scale":"1.28M","Zero-shot evaluation":true}. This record does not assert independent reproduction.

### ViT-B/16 (No pre-training)

Realistic Acc: 49.9. Result ID: 6993fda23a6c3148491a218d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pretraining Scale":"None","Zero-shot evaluation":true}. This record does not assert independent reproduction.

### DINOv2

Realistic Acc: 48. Result ID: 6993fda23a6c3148491a2189.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a00d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72181e209131cea546c3.md>)

[Implementation](<https://github.com/facebookresearch/dinov2>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Pretraining Scale":"142M","Zero-shot evaluation":true}. This record does not assert independent reproduction.

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