# Image Classification on ImageNet (test val) (Standard and Robust Accuracy)

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

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

Data updated: 2026-02-26T06:04:45.212Z

Evaluation of Image Classification performance on the combined test and validation splits of the ImageNet dataset, reporting both standard accuracy and robustness accuracy 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 (test val) |
| Metric | Standard 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

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

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

## Recorded results

| Method | Standard Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Nie et al. | 0.6822 | Not recorded | 68fa71671e209131cea5138a |
| Bai et al. | 0.6738 | Not recorded | 68fa71671e209131cea5138a |
| Salman et al. | 0.6402 | Not recorded | 68fa71671e209131cea5138a |
| Wang et al. | 0.6256 | Not recorded | 68fa71671e209131cea5138a |
| Wong et al. | 0.5562 | Not recorded | 68fa71671e209131cea5138a |

### Nie et al.

Standard Accuracy: 0.6822. Result ID: 6991ce3f3a6c3148490ab294.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71671e209131cea5138a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c841e209131cea3472d.md>)

Recorded evaluation configuration: {"Classifier":"ResNet50"}. This record does not assert independent reproduction.

### Bai et al.

Standard Accuracy: 0.6738. Result ID: 6991ce3f3a6c3148490ab293.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71671e209131cea5138a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69c91e209131cea23fbd.md>)

Recorded evaluation configuration: {"Classifier":"ResNet50"}. This record does not assert independent reproduction.

### Salman et al.

Standard Accuracy: 0.6402. Result ID: 6991ce3f3a6c3148490ab292.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71671e209131cea5138a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68e21e209131cea1ef57.md>)

[Implementation](<https://github.com/Microsoft/robust-models-transfer>)

Recorded evaluation configuration: {"Classifier":"ResNet50"}. This record does not assert independent reproduction.

### Wang et al.

Standard Accuracy: 0.6256. Result ID: 6991ce3f3a6c3148490ab290.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71671e209131cea5138a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea5091d.md>)

Recorded evaluation configuration: {"Classifier":"ResNet50"}. This record does not assert independent reproduction.

### Wong et al.

Standard Accuracy: 0.5562. Result ID: 6991ce3f3a6c3148490ab291.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71671e209131cea5138a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e51e209131cea12efc.md>)

Recorded evaluation configuration: {"Classifier":"ResNet50"}. This record does not assert independent reproduction.

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