# Image Classification on ImageNet (val) (Accuracy and Robustness)

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

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

Data updated: 2026-02-26T05:27:58.369Z

Evaluation of Image Classification performance on the validation split of the ImageNet dataset, reporting standard Accuracy alongside robustness metrics.

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 | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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-val-accuracy-and-robustness.md?metric=Accuracy>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| EfficientNet + SAT | 82.2 | Not recorded | 68fa6a531e209131cea275d2 |
| Prior art | 72.7 | Not recorded | 68fa6a531e209131cea275d2 |

### EfficientNet + SAT

Accuracy: 82.2. Result ID: 698e291effc3901de09b4990.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a531e209131cea275d2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a531e209131cea275d2.md>)

[Implementation](<https://github.com/cihangxie/SmoothAdversarialTraining>)

Recorded evaluation configuration: {"Architecture":"EfficientNet-L1"}. This record does not assert independent reproduction.

### Prior art

Accuracy: 72.7. Result ID: 698e291effc3901de09b498f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a531e209131cea275d2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa667f1e209131cea10a98.md>)

Recorded evaluation configuration: {"Architecture":"ResNet-152"}. This record does not assert independent reproduction.

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