# Image Classification on CIFAR-100 (test) (Accuracy Profile by Training Epoch)

Source: [Image Classification on CIFAR-100 (test) (Accuracy Profile by Training Epoch)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-accuracy-profile-by-training-epoch>)

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

Data updated: 2026-06-02T12:43:57.291Z

Evaluation of Image Classification performance on the CIFAR-100 test set, tracking Top-1 Accuracy progression at specific 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-100 (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-100-test-accuracy-profile-by-training-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-100-test-accuracy-profile-by-training-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-100-test-accuracy-profile-by-training-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 |
| --- | --- | --- | --- |
| Lion | 68 | Not recorded | 6a1e6447dbd7150506f85967 |
| LPSGDM | 67.47 | Not recorded | 6a1e6447dbd7150506f85967 |
| AdamW | 65.84 | Not recorded | 6a1e6447dbd7150506f85967 |
| Lion | 65.39 | Not recorded | 6a1e6447dbd7150506f85967 |
| SGD w/ Momentum | 63.34 | Not recorded | 6a1e6447dbd7150506f85967 |
| Lion | 55.92 | Not recorded | 6a1e6447dbd7150506f85967 |
| LPSGDM | 55.48 | Not recorded | 6a1e6447dbd7150506f85967 |
| SGD w/ Momentum | 54.21 | Not recorded | 6a1e6447dbd7150506f85967 |
| AdamW | 51.01 | Not recorded | 6a1e6447dbd7150506f85967 |
| LPSGDM | 48.03 | Not recorded | 6a1e6447dbd7150506f85967 |
| AdamW | 47.92 | Not recorded | 6a1e6447dbd7150506f85967 |
| SGD w/ Momentum | 44.12 | Not recorded | 6a1e6447dbd7150506f85967 |

### Lion

Top-1 Accuracy (Epoch 50): 68. Result ID: 6a1ecff7fbc373592c1a95fa.

[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.

### LPSGDM

Top-1 Accuracy (Epoch 50): 67.47. Result ID: 6a1ecff7fbc373592c1a95fb.

[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.

### AdamW

Top-1 Accuracy (Epoch 50): 65.84. Result ID: 6a1ecff7fbc373592c1a95f9.

[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): 65.39. Result ID: 6a1ecff7fbc373592c1a95f6.

[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): 63.34. Result ID: 6a1ecff7fbc373592c1a95f8.

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

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

### Lion

Top-1 Accuracy (Epoch 50): 55.92. Result ID: 6a1ecff7fbc373592c1a95f2.

[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.

### LPSGDM

Top-1 Accuracy (Epoch 50): 55.48. Result ID: 6a1ecff7fbc373592c1a95f3.

[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): 54.21. Result ID: 6a1ecff7fbc373592c1a95f0.

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

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

### AdamW

Top-1 Accuracy (Epoch 50): 51.01. Result ID: 6a1ecff7fbc373592c1a95f1.

[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.

### LPSGDM

Top-1 Accuracy (Epoch 50): 48.03. Result ID: 6a1ecff7fbc373592c1a95f7.

[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): 47.92. Result ID: 6a1ecff7fbc373592c1a95f5.

[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.

### SGD w/ Momentum

Top-1 Accuracy (Epoch 50): 44.12. Result ID: 6a1ecff7fbc373592c1a95f4.

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

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

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