# Image Classification on CIFAR-10 ID-TEST DEEPNETS-1M (test)

Source: [Image Classification on CIFAR-10 ID-TEST DEEPNETS-1M (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-id-test-deepnets-1m-test>)

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

Data updated: 2026-02-26T05:36:03.949Z

Evaluation of Image Classification performance on the test split of the CIFAR-10 ID-TEST DEEPNETS-1M dataset.

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 ID-TEST DEEPNETS-1M (test) |
| Metric | Avg Accuracy |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Avg Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-id-test-deepnets-1m-test.md?metric=Avg%20Accuracy>): Higher is better; unit: SCALAR.

- [Max Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-id-test-deepnets-1m-test.md?metric=Max%20Accuracy>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Avg Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SGD | 0.885 | Not recorded | 68fa6b1b1e209131cea2c408 |
| Adam | 0.84 | Not recorded | 68fa6b1b1e209131cea2c408 |
| SGD | 0.692 | Not recorded | 68fa6b1b1e209131cea2c408 |
| GHN-2 | 0.669 | Not recorded | 68fa6b1b1e209131cea2c408 |
| GHN-1 | 0.514 | Not recorded | 68fa6b1b1e209131cea2c408 |
| SGD | 0.461 | Not recorded | 68fa6b1b1e209131cea2c408 |
| MLP | 0.422 | Not recorded | 68fa6b1b1e209131cea2c408 |

### SGD

Avg Accuracy: 0.885. Result ID: 698e5dbeffc3901de09cfb45.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1b1e209131cea2c408.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63671e209131ce9fe75b.md>)

Recorded evaluation configuration: {"#upd+":"25x10^3","training\_duration":"50 epochs"}. This record does not assert independent reproduction.

### Adam

Avg Accuracy: 0.84. Result ID: 698e5dbeffc3901de09cfb46.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1b1e209131cea2c408.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63171e209131ce9fca0b.md>)

Recorded evaluation configuration: {"#upd+":"25x10^3","training\_duration":"50 epochs"}. This record does not assert independent reproduction.

### SGD

Avg Accuracy: 0.692. Result ID: 698e5dbeffc3901de09cfb44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1b1e209131cea2c408.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63671e209131ce9fe75b.md>)

Recorded evaluation configuration: {"#upd+":"2.5x10^3","training\_duration":"5 epochs"}. This record does not assert independent reproduction.

### GHN-2

Avg Accuracy: 0.669. Result ID: 698e5dbeffc3901de09cfb42.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1b1e209131cea2c408.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b1b1e209131cea2c408.md>)

[Implementation](<https://github.com/facebookresearch/ppuda>)

Recorded evaluation configuration: {"#upd+":"1"}. This record does not assert independent reproduction.

### GHN-1

Avg Accuracy: 0.514. Result ID: 698e5dbeffc3901de09cfb41.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1b1e209131cea2c408.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68f01e209131cea1f17b.md>)

Recorded evaluation configuration: {"#upd+":"1"}. This record does not assert independent reproduction.

### SGD

Avg Accuracy: 0.461. Result ID: 698e5dbeffc3901de09cfb43.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1b1e209131cea2c408.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63671e209131ce9fe75b.md>)

Recorded evaluation configuration: {"#upd+":"0.5x10^3","training\_duration":"1 epoch"}. This record does not assert independent reproduction.

### MLP

Avg Accuracy: 0.422. Result ID: 698e5dbeffc3901de09cfb40.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b1b1e209131cea2c408.md>)

Recorded evaluation configuration: {"#upd+":"1"}. This record does not assert independent reproduction.

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