# Image Classification on CIFAR-10 (test) (Standard and Robust Accuracy)

Source: [Image Classification on CIFAR-10 (test) (Standard and Robust Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-standard-and-robust-accuracy>)

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

Data updated: 2026-02-27T08:38:37.523Z

Evaluation of Image Classification performance on the CIFAR-10 test set, reporting both standard accuracy and a specific robustness accuracy metric.

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) | CIFAR-10 (test) |
| Metric | Standard Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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-cifar-10-test-standard-and-robust-accuracy.md?metric=Standard%20Accuracy>): Higher is better; unit: PERCENT.

- [Robust Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-standard-and-robust-accuracy.md?metric=Robust%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Standard Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Base Classifier | 95.19 | Not recorded | 68fa71031e209131cea4e879 |
| ScoreOpt-N | 93.1 | Not recorded | 68fa71031e209131cea4e879 |
| ScoreOpt-O | 91.85 | Not recorded | 68fa71031e209131cea4e879 |
| Gowal et al. | 90.9 | Not recorded | 68fa71031e209131cea4e879 |
| Rony et al. | 89.05 | Not recorded | 68fa71031e209131cea4e879 |
| Rice et al. | 88.67 | Not recorded | 68fa71031e209131cea4e879 |
| Wu et al. | 88.51 | Not recorded | 68fa71031e209131cea4e879 |
| Ding et al. | 88.02 | Not recorded | 68fa71031e209131cea4e879 |

### Base Classifier

Standard Accuracy: 95.19. Result ID: 69a157f535dfcabb00e66908.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e879.md>)

Recorded evaluation configuration: {"Threat Model":"l2(ϵ = 0.5)"}. This record does not assert independent reproduction.

### ScoreOpt-N

Standard Accuracy: 93.1. Result ID: 69a157f535dfcabb00e6690f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e879.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e879.md>)

[Implementation](<https://github.com/zzzhangboya/ScoreOpt.git>)

Recorded evaluation configuration: {"Threat Model":"l2(ϵ = 0.5)"}. This record does not assert independent reproduction.

### ScoreOpt-O

Standard Accuracy: 91.85. Result ID: 69a157f535dfcabb00e6690e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e879.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e879.md>)

[Implementation](<https://github.com/zzzhangboya/ScoreOpt.git>)

Recorded evaluation configuration: {"Threat Model":"l2(ϵ = 0.5)"}. This record does not assert independent reproduction.

### Gowal et al.

Standard Accuracy: 90.9. Result ID: 69a157f535dfcabb00e6690d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e879.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69981e209131cea22f05.md>)

Recorded evaluation configuration: {"Threat Model":"l2(ϵ = 0.5)"}. This record does not assert independent reproduction.

### Rony et al.

Standard Accuracy: 89.05. Result ID: 69a157f535dfcabb00e66909.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e879.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65891e209131cea0aec5.md>)

Recorded evaluation configuration: {"Threat Model":"l2(ϵ = 0.5)"}. This record does not assert independent reproduction.

### Rice et al.

Standard Accuracy: 88.67. Result ID: 69a157f535dfcabb00e6690b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e879.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67251e209131cea14aa2.md>)

Recorded evaluation configuration: {"Threat Model":"l2(ϵ = 0.5)"}. This record does not assert independent reproduction.

### Wu et al.

Standard Accuracy: 88.51. Result ID: 69a157f535dfcabb00e6690c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e879.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa687e1e209131cea1c519.md>)

Recorded evaluation configuration: {"Threat Model":"l2(ϵ = 0.5)"}. This record does not assert independent reproduction.

### Ding et al.

Standard Accuracy: 88.02. Result ID: 69a157f535dfcabb00e6690a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71031e209131cea4e879.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa671f1e209131cea14676.md>)

Recorded evaluation configuration: {"Threat Model":"l2(ϵ = 0.5)"}. This record does not assert independent reproduction.

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