# Image Classification on ImageNet (val) (Accuracy, Throughput, and MACs)

Source: [Image Classification on ImageNet (val) (Accuracy, Throughput, and MACs)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-accuracy-throughput-and-macs>)

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

Data updated: 2026-02-26T06:06:58.369Z

Evaluation of Image Classification performance on the validation split of the ImageNet dataset, reporting Top-1/Top-5 accuracy alongside inference throughput and computational cost (MACs).

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

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

- [Throughput (images/s)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-accuracy-throughput-and-macs.md?metric=Throughput%20(images%2Fs)>): Higher is better; unit: TIME.

- [MACs (G)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-accuracy-throughput-and-macs.md?metric=MACs%20(G)>): Lower is better; unit: SIZE.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LV-ViT-S | 83.3 | Not recorded | 68fa6c3c1e209131cea32f0b |
| EViT | 83 | Not recorded | 68fa6c3c1e209131cea32f0b |
| EViT | 82.5 | Not recorded | 68fa6c3c1e209131cea32f0b |

### LV-ViT-S

Top-1 Accuracy: 83.3. Result ID: 698efa163a6c314849f43948.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c3c1e209131cea32f0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1d1e209131cea25fd2.md>)

[Implementation](<https://github.com/zihangJiang/TokenLabeling>)

Recorded evaluation configuration: {"Keep rate":"1.0"}. This record does not assert independent reproduction.

### EViT

Top-1 Accuracy: 83. Result ID: 698efa163a6c314849f43949.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c3c1e209131cea32f0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c3c1e209131cea32f0b.md>)

[Implementation](<https://github.com/youweiliang/evit>)

Recorded evaluation configuration: {"Keep rate":"0.7","Backbone":"LV-ViT-S"}. This record does not assert independent reproduction.

### EViT

Top-1 Accuracy: 82.5. Result ID: 698efa163a6c314849f4394a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c3c1e209131cea32f0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c3c1e209131cea32f0b.md>)

[Implementation](<https://github.com/youweiliang/evit>)

Recorded evaluation configuration: {"Keep rate":"0.5","Backbone":"LV-ViT-S"}. This record does not assert independent reproduction.

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