# Image Classification on MNIST (Accuracy and Width Statistics)

Source: [Image Classification on MNIST (Accuracy and Width Statistics)](<https://www.sota2.com/research/sota/image-classification-on-mnist-accuracy-and-width-statistics>)

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

Data updated: 2026-02-26T05:34:19.958Z

Evaluation of Image Classification performance on the MNIST dataset, reporting mean and standard deviation for accuracy and model width metrics.

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) | MNIST |
| Metric | Accuracy (Mean) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Accuracy (Mean)](<https://www.sota2.com/research/sota/image-classification-on-mnist-accuracy-and-width-statistics.md?metric=Accuracy%20(Mean)>): Higher is better; unit: PERCENT.

- [Accuracy (Std)](<https://www.sota2.com/research/sota/image-classification-on-mnist-accuracy-and-width-statistics.md?metric=Accuracy%20(Std)>): Lower is better; unit: PERCENT.

- [Total Width (Mean)](<https://www.sota2.com/research/sota/image-classification-on-mnist-accuracy-and-width-statistics.md?metric=Total%20Width%20(Mean)>): Higher is better; unit: OTHER.

- [Total Width (Std)](<https://www.sota2.com/research/sota/image-classification-on-mnist-accuracy-and-width-statistics.md?metric=Total%20Width%20(Std)>): Higher is better; unit: OTHER.

## Recorded results

| Method | Accuracy (Mean) | Result date | Report paper |
| --- | --- | --- | --- |
| AWN | 99.7 | Not recorded | 68fa78bd1e209131cea7a28d |
| Linear Classifier (Fixed) | 99.6 | Not recorded | 68fa78bd1e209131cea7a28d |

### AWN

Accuracy (Mean): 99.7. Result ID: 699a8a435698665ec4146095.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78bd1e209131cea7a28d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78bd1e209131cea7a28d.md>)

Recorded evaluation configuration: {"Method":"AWN"}. This record does not assert independent reproduction.

### Linear Classifier (Fixed)

Accuracy (Mean): 99.6. Result ID: 699a8a435698665ec4146094.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78bd1e209131cea7a28d.md>)

Recorded evaluation configuration: {"Method":"Fixed","Downstream Classifier":"Linear model"}. This record does not assert independent reproduction.

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