# Image Classification on ImageNet-1k (val) (Balanced Accuracy)

Source: [Image Classification on ImageNet-1k (val) (Balanced Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-balanced-accuracy>)

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

Data updated: 2026-07-03T08:10:12.005Z

Evaluation of Image Classification performance on the validation split of ImageNet-1K, reporting Top-1 and Top-5 Balanced Accuracy.

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 Classification |
| Dataset (including any stated split) | ImageNet-1k (val) |
| Metric | Top-1 Balanced Accuracy |
| Unit | PERCENT |
| 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

- [Top-1 Balanced Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-balanced-accuracy.md?metric=Top-1%20Balanced%20Accuracy>): Higher is better; unit: PERCENT.

- [Top-5 Balanced Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-balanced-accuracy.md?metric=Top-5%20Balanced%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Balanced Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DINOv3 | 79 | Not recorded | 6a474218143ebdcacacc5ddd |
| DINOv3 | 77.6 | Not recorded | 6a474218143ebdcacacc5ddd |
| SlotMIM | 55.2 | Not recorded | 6a474218143ebdcacacc5ddd |
| Object LeJEPA | 53.9 | Not recorded | 6a474218143ebdcacacc5ddd |
| Image LeJEPA | 47.3 | Not recorded | 6a474218143ebdcacacc5ddd |
| SlotMIM | 46.7 | Not recorded | 6a474218143ebdcacacc5ddd |
| Image LeJEPA | 46.3 | Not recorded | 6a474218143ebdcacacc5ddd |

### DINOv3

Top-1 Balanced Accuracy: 79. Result ID: 6a476e6260b88bb33993884c.

[Reporting paper](<https://www.sota2.com/research/paper/6a474218143ebdcacacc5ddd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69019f863ef7ccd74e5e3b87.md>)

Recorded evaluation configuration: {"Protocol":"Linear-probe","Representation":"\[CLS\] token"}. This record does not assert independent reproduction.

### DINOv3

Top-1 Balanced Accuracy: 77.6. Result ID: 6a476e6260b88bb33993884b.

[Reporting paper](<https://www.sota2.com/research/paper/6a474218143ebdcacacc5ddd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69019f863ef7ccd74e5e3b87.md>)

Recorded evaluation configuration: {"Protocol":"Linear-probe","Representation":"Averaged patch tokens"}. This record does not assert independent reproduction.

### SlotMIM

Top-1 Balanced Accuracy: 55.2. Result ID: 6a476e6260b88bb339938848.

[Reporting paper](<https://www.sota2.com/research/paper/6a474218143ebdcacacc5ddd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa778e1e209131cea73ddb.md>)

[Implementation](<https://github.com/CVMI-Lab/SlotMIM>)

Recorded evaluation configuration: {"Protocol":"Linear-probe","Representation":"Averaged patch tokens","Training epochs":"800"}. This record does not assert independent reproduction.

### Object LeJEPA

Top-1 Balanced Accuracy: 53.9. Result ID: 6a476e6260b88bb33993884a.

[Reporting paper](<https://www.sota2.com/research/paper/6a474218143ebdcacacc5ddd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a474218143ebdcacacc5ddd.md>)

Recorded evaluation configuration: {"Protocol":"Linear-probe","Representation":"Averaged patch tokens"}. This record does not assert independent reproduction.

### Image LeJEPA

Top-1 Balanced Accuracy: 47.3. Result ID: 6a476e6260b88bb339938847.

[Reporting paper](<https://www.sota2.com/research/paper/6a474218143ebdcacacc5ddd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691414922828b7cc6937ec28.md>)

Recorded evaluation configuration: {"Protocol":"Linear-probe","Representation":"\[CLS\] token"}. This record does not assert independent reproduction.

### SlotMIM

Top-1 Balanced Accuracy: 46.7. Result ID: 6a476e6260b88bb339938849.

[Reporting paper](<https://www.sota2.com/research/paper/6a474218143ebdcacacc5ddd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa778e1e209131cea73ddb.md>)

[Implementation](<https://github.com/CVMI-Lab/SlotMIM>)

Recorded evaluation configuration: {"Protocol":"Linear-probe","Representation":"Averaged patch tokens"}. This record does not assert independent reproduction.

### Image LeJEPA

Top-1 Balanced Accuracy: 46.3. Result ID: 6a476e6260b88bb339938846.

[Reporting paper](<https://www.sota2.com/research/paper/6a474218143ebdcacacc5ddd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691414922828b7cc6937ec28.md>)

Recorded evaluation configuration: {"Protocol":"Linear-probe","Representation":"Averaged patch tokens"}. This record does not assert independent reproduction.

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