# Image Classification on ImageNet-1K 100% labels (train)

Source: [Image Classification on ImageNet-1K 100% labels (train)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-100-percent-labels-train>)

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

Data updated: 2026-02-27T07:12:57.409Z

Evaluation of Image Classification performance on the training split of the full 1000-class ImageNet dataset, measured using Top-1 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 100% labels (train) |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-100-percent-labels-train.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Data2Vec | 84.2 | Not recorded | 68fa6c591e209131cea33793 |
| MaskFeat | 84 | Not recorded | 68fa6c591e209131cea33793 |
| iBOT | 83.8 | Not recorded | 68fa6c591e209131cea33793 |
| SimMIM | 83.8 | Not recorded | 68fa6c591e209131cea33793 |
| DINO | 83.6 | Not recorded | 68fa6c591e209131cea33793 |
| MAE | 83.6 | Not recorded | 68fa6c591e209131cea33793 |
| MSN | 83.4 | Not recorded | 68fa6c591e209131cea33793 |
| BEiT | 83.2 | Not recorded | 68fa6c591e209131cea33793 |

### Data2Vec

Top-1 Accuracy: 84.2. Result ID: 69a143f735dfcabb00e5e4ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dbb1e209131cea3bad1.md>)

[Implementation](<https://www.sota2.com/www.github.com/pytorch/fairseq/tree/master/examples/data2vec>)

Recorded evaluation configuration: {"Architecture":"ViT-B/16","Pretrain Epochs":"800","Evaluation protocol":"End-to-end fine-tuning"}. This record does not assert independent reproduction.

### MaskFeat

Top-1 Accuracy: 84. Result ID: 69a143f735dfcabb00e5e4ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e581e209131cea3f317.md>)

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

Recorded evaluation configuration: {"Architecture":"ViT-B/16","Evaluation protocol":"End-to-end fine-tuning"}. This record does not assert independent reproduction.

### iBOT

Top-1 Accuracy: 83.8. Result ID: 69a143f735dfcabb00e5e4a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

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

Recorded evaluation configuration: {"Architecture":"ViT-B/16","Pretrain Epochs":"800","Evaluation protocol":"End-to-end fine-tuning"}. This record does not assert independent reproduction.

### SimMIM

Top-1 Accuracy: 83.8. Result ID: 69a143f735dfcabb00e5e4aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c5b1e209131cea33891.md>)

[Implementation](<https://github.com/microsoft/SimMIM>)

Recorded evaluation configuration: {"Architecture":"ViT-B/16","Evaluation protocol":"End-to-end fine-tuning"}. This record does not assert independent reproduction.

### DINO

Top-1 Accuracy: 83.6. Result ID: 69a143f735dfcabb00e5e4a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

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

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

Recorded evaluation configuration: {"Architecture":"ViT-B/16","Pretrain Epochs":"800","Evaluation protocol":"End-to-end fine-tuning"}. This record does not assert independent reproduction.

### MAE

Top-1 Accuracy: 83.6. Result ID: 69a143f735dfcabb00e5e4a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

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

Recorded evaluation configuration: {"Architecture":"ViT-B/16","Pretrain Epochs":"1600","Evaluation protocol":"End-to-end fine-tuning"}. This record does not assert independent reproduction.

### MSN

Top-1 Accuracy: 83.4. Result ID: 69a143f735dfcabb00e5e4ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

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

Recorded evaluation configuration: {"Architecture":"ViT-B/16","Pretrain Epochs":"600","Evaluation protocol":"End-to-end fine-tuning"}. This record does not assert independent reproduction.

### BEiT

Top-1 Accuracy: 83.2. Result ID: 69a143f735dfcabb00e5e4a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d5a1e209131cea39630.md>)

[Implementation](<https://aka.ms/beit>)

Recorded evaluation configuration: {"Architecture":"ViT-B/16","Pretrain Epochs":"800","Evaluation protocol":"End-to-end fine-tuning"}. This record does not assert independent reproduction.

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