# Image Classification on ImageNet-1k (val) (Top-1 Ret. and Final Accuracy)

Source: [Image Classification on ImageNet-1k (val) (Top-1 Ret. and Final Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-top-1-ret-and-final-accuracy>)

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

Data updated: 2026-04-02T09:17:19.178Z

Evaluation of Image Classification performance on the validation split of ImageNet-1K, reporting Top-1 Retained Accuracy and Top-1 Final 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 Ret. Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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 Ret. Acc](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-top-1-ret-and-final-accuracy.md?metric=Top-1%20Ret.%20Acc>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Top-1 Ret. Acc | Result date | Report paper |
| --- | --- | --- | --- |
| NViT | 81.13 | Not recorded | 68fa7a0b1e209131cea80c66 |
| VBP | 72.37 | Not recorded | 68fa7a0b1e209131cea80c66 |
| NViT | 69.1 | Not recorded | 68fa7a0b1e209131cea80c66 |

### NViT

Top-1 Ret. Acc: 81.13. Result ID: 69ce341c47f34ce924b79c8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a0b1e209131cea80c66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee31e209131cea42aab.md>)

Recorded evaluation configuration: {"Epochs":"50","Param. (M)":"56.37"}. This record does not assert independent reproduction.

### VBP

Top-1 Ret. Acc: 72.37. Result ID: 69ce341c47f34ce924b79c8c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a0b1e209131cea80c66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a0b1e209131cea80c66.md>)

Recorded evaluation configuration: {"Epochs":"1","Param. (M)":"56.18"}. This record does not assert independent reproduction.

### NViT

Top-1 Ret. Acc: 69.1. Result ID: 69ce341c47f34ce924b79c8b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a0b1e209131cea80c66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee31e209131cea42aab.md>)

Recorded evaluation configuration: {"Epochs":"1","Param. (M)":"56.85"}. This record does not assert independent reproduction.

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