# Image Classification on CIFAR-10 (test) (Top-1 Accuracy vs Epoch)

Source: [Image Classification on CIFAR-10 (test) (Top-1 Accuracy vs Epoch)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-top-1-accuracy-vs-epoch>)

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

Data updated: 2026-06-02T12:43:57.331Z

Evaluation of Image Classification performance on the CIFAR-10 test set, reporting Top-1 Accuracy measured specifically at training epochs 50, 100, and 200.

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 | Top-1 Accuracy (Epoch 50) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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 (Epoch 50)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-top-1-accuracy-vs-epoch.md?metric=Top-1%20Accuracy%20(Epoch%2050)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (Epoch 100)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-top-1-accuracy-vs-epoch.md?metric=Top-1%20Accuracy%20(Epoch%20100)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (Epoch 200)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-top-1-accuracy-vs-epoch.md?metric=Top-1%20Accuracy%20(Epoch%20200)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy (Epoch 50) | Result date | Report paper |
| --- | --- | --- | --- |
| LPSGDM | 92.22 | Not recorded | 6a1e6447dbd7150506f85967 |
| LPSGDM | 92.12 | Not recorded | 6a1e6447dbd7150506f85967 |
| AdamW | 91.78 | Not recorded | 6a1e6447dbd7150506f85967 |
| AdamW | 91.65 | Not recorded | 6a1e6447dbd7150506f85967 |
| Lion | 91.15 | Not recorded | 6a1e6447dbd7150506f85967 |
| Lion | 90.53 | Not recorded | 6a1e6447dbd7150506f85967 |
| SGD w/ Momentum | 88.77 | Not recorded | 6a1e6447dbd7150506f85967 |
| SGD w/ Momentum | 87.57 | Not recorded | 6a1e6447dbd7150506f85967 |
| LPSGDM | 86.15 | Not recorded | 6a1e6447dbd7150506f85967 |
| SGD w/ Momentum | 85.88 | Not recorded | 6a1e6447dbd7150506f85967 |
| Lion | 85.05 | Not recorded | 6a1e6447dbd7150506f85967 |
| AdamW | 83.54 | Not recorded | 6a1e6447dbd7150506f85967 |

### LPSGDM

Top-1 Accuracy (Epoch 50): 92.22. Result ID: 6a1ecff7fbc373592c1a9613.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

Recorded evaluation configuration: {"Model":"ResNet-50"}. This record does not assert independent reproduction.

### LPSGDM

Top-1 Accuracy (Epoch 50): 92.12. Result ID: 6a1ecff7fbc373592c1a960f.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction.

### AdamW

Top-1 Accuracy (Epoch 50): 91.78. Result ID: 6a1ecff7fbc373592c1a960d.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa55761e209131ce9946db.md>)

Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction.

### AdamW

Top-1 Accuracy (Epoch 50): 91.65. Result ID: 6a1ecff7fbc373592c1a9611.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa55761e209131ce9946db.md>)

Recorded evaluation configuration: {"Model":"ResNet-50"}. This record does not assert independent reproduction.

### Lion

Top-1 Accuracy (Epoch 50): 91.15. Result ID: 6a1ecff7fbc373592c1a9612.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea448e3.md>)

[Implementation](<https://github.com/google/automl/tree/master/lion>)

Recorded evaluation configuration: {"Model":"ResNet-50"}. This record does not assert independent reproduction.

### Lion

Top-1 Accuracy (Epoch 50): 90.53. Result ID: 6a1ecff7fbc373592c1a960e.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea448e3.md>)

[Implementation](<https://github.com/google/automl/tree/master/lion>)

Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction.

### SGD w/ Momentum

Top-1 Accuracy (Epoch 50): 88.77. Result ID: 6a1ecff7fbc373592c1a960c.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

Recorded evaluation configuration: {"Model":"ResNet-18"}. This record does not assert independent reproduction.

### SGD w/ Momentum

Top-1 Accuracy (Epoch 50): 87.57. Result ID: 6a1ecff7fbc373592c1a9610.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

Recorded evaluation configuration: {"Model":"ResNet-50"}. This record does not assert independent reproduction.

### LPSGDM

Top-1 Accuracy (Epoch 50): 86.15. Result ID: 6a1ecff7fbc373592c1a960b.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

Recorded evaluation configuration: {"Model":"VGG-11"}. This record does not assert independent reproduction.

### SGD w/ Momentum

Top-1 Accuracy (Epoch 50): 85.88. Result ID: 6a1ecff7fbc373592c1a9608.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

Recorded evaluation configuration: {"Model":"VGG-11"}. This record does not assert independent reproduction.

### Lion

Top-1 Accuracy (Epoch 50): 85.05. Result ID: 6a1ecff7fbc373592c1a960a.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea448e3.md>)

[Implementation](<https://github.com/google/automl/tree/master/lion>)

Recorded evaluation configuration: {"Model":"VGG-11"}. This record does not assert independent reproduction.

### AdamW

Top-1 Accuracy (Epoch 50): 83.54. Result ID: 6a1ecff7fbc373592c1a9609.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa55761e209131ce9946db.md>)

Recorded evaluation configuration: {"Model":"VGG-11"}. This record does not assert independent reproduction.

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