# Image Classification on CIFAR-10 (Model Architecture Comparison)

Source: [Image Classification on CIFAR-10 (Model Architecture Comparison)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-model-architecture-comparison>)

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

Data updated: 2026-02-26T05:34:48.833Z

Evaluation of standard Image Classification performance on the CIFAR-10 dataset, reporting accuracy results across various baseline model architectures (AlexNet, ResNet18, VGG11, ViT).

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 |
| Metric | AlexNet Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [AlexNet Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-model-architecture-comparison.md?metric=AlexNet%20Accuracy>): Higher is better; unit: PERCENT.

- [ResNet18 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-model-architecture-comparison.md?metric=ResNet18%20Accuracy>): Higher is better; unit: PERCENT.

- [VGG11 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-model-architecture-comparison.md?metric=VGG11%20Accuracy>): Higher is better; unit: PERCENT.

- [ViT Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-model-architecture-comparison.md?metric=ViT%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-model-architecture-comparison.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AlexNet Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DC | 30.1 | Not recorded | 68fa6f311e209131cea44584 |
| MTT | 27.9 | Not recorded | 68fa6f311e209131cea44584 |
| MTT | 27.4 | Not recorded | 68fa6f311e209131cea44584 |
| MTT | 26.8 | Not recorded | 68fa6f311e209131cea44584 |
| DC | 26 | Not recorded | 68fa6f311e209131cea44584 |
| DC | 25.9 | Not recorded | 68fa6f311e209131cea44584 |
| DM | 25.1 | Not recorded | 68fa6f311e209131cea44584 |
| DM | 23.7 | Not recorded | 68fa6f311e209131cea44584 |
| DM | 22.9 | Not recorded | 68fa6f311e209131cea44584 |

### DC

AlexNet Accuracy: 30.1. Result ID: 69909b7a3a6c31484901d26a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Distillation Space":"GLAD (Rand G)"}. This record does not assert independent reproduction.

### MTT

AlexNet Accuracy: 27.9. Result ID: 69909b7a3a6c31484901d268.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Distillation Space":"GLAD (Trained G)"}. This record does not assert independent reproduction.

### MTT

AlexNet Accuracy: 27.4. Result ID: 69909b7a3a6c31484901d267.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Distillation Space":"GLAD (Rand G)"}. This record does not assert independent reproduction.

### MTT

AlexNet Accuracy: 26.8. Result ID: 69909b7a3a6c31484901d266.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Distillation Space":"Pixel"}. This record does not assert independent reproduction.

### DC

AlexNet Accuracy: 26. Result ID: 69909b7a3a6c31484901d26b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Distillation Space":"GLAD (Trained G)"}. This record does not assert independent reproduction.

### DC

AlexNet Accuracy: 25.9. Result ID: 69909b7a3a6c31484901d269.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Distillation Space":"Pixel"}. This record does not assert independent reproduction.

### DM

AlexNet Accuracy: 25.1. Result ID: 69909b7b3a6c31484901d26e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Distillation Space":"GLAD (Trained G)"}. This record does not assert independent reproduction.

### DM

AlexNet Accuracy: 23.7. Result ID: 69909b7b3a6c31484901d26d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Distillation Space":"GLAD (Rand G)"}. This record does not assert independent reproduction.

### DM

AlexNet Accuracy: 22.9. Result ID: 69909b7b3a6c31484901d26c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Distillation Space":"Pixel"}. This record does not assert independent reproduction.

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