# Image Classification on ImageNet 1K (Accuracy, Bits per Token, Compression Ratio)

Source: [Image Classification on ImageNet 1K (Accuracy, Bits per Token, Compression Ratio)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-accuracy-bits-per-token-compression-ratio>)

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

Data updated: 2026-05-28T07:31:29.553Z

Evaluation of Image Classification performance on the ImageNet-1K dataset, reporting standard Accuracy alongside model size and compression efficiency metrics (Total Bits per Token and Compression Ratio).

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 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-accuracy-bits-per-token-compression-ratio.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Total Bits per Token](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-accuracy-bits-per-token-compression-ratio.md?metric=Total%20Bits%20per%20Token>): Lower is better; unit: SCALAR.

- [Compression Ratio](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-accuracy-bits-per-token-compression-ratio.md?metric=Compression%20Ratio>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ViT-Base | 80.32 | Not recorded | 68fa78c01e209131cea7a48b |
| ASTRA | 80.28 | Not recorded | 68fa78c01e209131cea7a48b |
| ASTRA | 78.8 | Not recorded | 68fa78c01e209131cea7a48b |
| ASTRA | 77.39 | Not recorded | 68fa78c01e209131cea7a48b |

### ViT-Base

Accuracy: 80.32. Result ID: 6a17ee5cfbc373592c1149d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c01e209131cea7a48b.md>)

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

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

Recorded evaluation configuration: {"Model":"ViT-Base"}. This record does not assert independent reproduction.

### ASTRA

Accuracy: 80.28. Result ID: 6a17ee5cfbc373592c1149d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c01e209131cea7a48b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c01e209131cea7a48b.md>)

Recorded evaluation configuration: {"Model":"ViT-Base","#Groups":"32"}. This record does not assert independent reproduction.

### ASTRA

Accuracy: 78.8. Result ID: 6a17ee5cfbc373592c1149d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c01e209131cea7a48b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c01e209131cea7a48b.md>)

Recorded evaluation configuration: {"Model":"ViT-Base","#Groups":"16"}. This record does not assert independent reproduction.

### ASTRA

Accuracy: 77.39. Result ID: 6a17ee5cfbc373592c1149d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c01e209131cea7a48b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c01e209131cea7a48b.md>)

Recorded evaluation configuration: {"Model":"ViT-Base","#Groups":"1"}. This record does not assert independent reproduction.

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