# Image Classification on ImageNet (val) (Top-1 Accuracy and Error)

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

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

Data updated: 2026-02-26T06:06:57.547Z

Evaluation of Image Classification performance on the validation split of the ImageNet dataset, reporting Top-1 Accuracy and average error rate.

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 | 5 of 5 |
| 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-top-1-accuracy-and-error.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Error Rate](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-top-1-accuracy-and-error.md?metric=Average%20Error%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Full Attention | 81.7 | Not recorded | 68fa6b2b1e209131cea2c7d5 |
| Scatterbrain | 80.7 | Not recorded | 68fa6b2b1e209131cea2c7d5 |
| Performer | 80.1 | Not recorded | 68fa6b2b1e209131cea2c7d5 |
| SMYRF | 79.8 | Not recorded | 68fa6b2b1e209131cea2c7d5 |
| Baseline SMYRF + Performer | 79.7 | Not recorded | 68fa6b2b1e209131cea2c7d5 |

### Full Attention

Top-1 Accuracy: 81.7. Result ID: 698e6480ffc3901de09d3651.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2b1e209131cea2c7d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"Backbone":"T2T-ViT","Attention Replacement":"Full Attention"}. This record does not assert independent reproduction.

### Scatterbrain

Top-1 Accuracy: 80.7. Result ID: 698e6480ffc3901de09d3655.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2b1e209131cea2c7d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2b1e209131cea2c7d5.md>)

[Implementation](<https://github.com/HazyResearch/scatterbrain>)

Recorded evaluation configuration: {"Backbone":"T2T-ViT","Attention Replacement":"Scatterbrain"}. This record does not assert independent reproduction.

### Performer

Top-1 Accuracy: 80.1. Result ID: 698e6480ffc3901de09d3653.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2b1e209131cea2c7d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d699.md>)

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

Recorded evaluation configuration: {"Backbone":"T2T-ViT","Attention Replacement":"Performer"}. This record does not assert independent reproduction.

### SMYRF

Top-1 Accuracy: 79.8. Result ID: 698e6480ffc3901de09d3652.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2b1e209131cea2c7d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa687d1e209131cea1c44b.md>)

Recorded evaluation configuration: {"Backbone":"T2T-ViT","Attention Replacement":"SMYRF"}. This record does not assert independent reproduction.

### Baseline SMYRF + Performer

Top-1 Accuracy: 79.7. Result ID: 698e6480ffc3901de09d3654.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b2b1e209131cea2c7d5.md>)

Recorded evaluation configuration: {"Backbone":"T2T-ViT","Attention Replacement":"SMYRF + Performer"}. This record does not assert independent reproduction.

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