# Image Classification on MNIST (test) (Mean/Std/Max Accuracy & Loss)

Source: [Image Classification on MNIST (test) (Mean/Std/Max Accuracy & Loss)](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-mean-std-max-accuracy-and-loss>)

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

Data updated: 2026-02-27T12:23:04.578Z

Evaluation of standard Image Classification performance on the MNIST test set, reporting mean accuracy, standard deviation, maximum test accuracy, and loss.

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 (test) |
| Metric | Mean Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

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

- [Mean Accuracy Std](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-mean-std-max-accuracy-and-loss.md?metric=Mean%20Accuracy%20Std>): Lower is better; unit: SCALAR.

- [Max Test Accuracy](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-mean-std-max-accuracy-and-loss.md?metric=Max%20Test%20Accuracy>): Higher is better; unit: PERCENT.

- [Loss](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-mean-std-max-accuracy-and-loss.md?metric=Loss>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Mean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GEGO | 97.62 | Not recorded | 6971af08e25ad2fa9d1ed987 |
| GEO | 97.46 | Not recorded | 6971af08e25ad2fa9d1ed987 |
| GA | 97.12 | Not recorded | 6971af08e25ad2fa9d1ed987 |

### GEGO

Mean Accuracy: 97.62. Result ID: 69a18c9335dfcabb00e7c5a8.

[Reporting paper](<https://www.sota2.com/research/paper/6971af08e25ad2fa9d1ed987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6971af08e25ad2fa9d1ed987.md>)

Recorded evaluation configuration: {"Number of Neurons":"\[378, 191, 220, 106\]","Dropout Rate":"\[0, 0.1, 0, 0\]","Batch Size":"224","Learning Rate":"0.01"}. This record does not assert independent reproduction.

### GEO

Mean Accuracy: 97.46. Result ID: 69a18c9335dfcabb00e7c5a7.

[Reporting paper](<https://www.sota2.com/research/paper/6971af08e25ad2fa9d1ed987.md>)

Recorded evaluation configuration: {"Number of Neurons":"\[512, 135, 504, 220\]","Dropout Rate":"\[0.5, 0.5, 0, 0\]","Batch Size":"32","Learning Rate":"0.01"}. This record does not assert independent reproduction.

### GA

Mean Accuracy: 97.12. Result ID: 69a18c9335dfcabb00e7c5a9.

[Reporting paper](<https://www.sota2.com/research/paper/6971af08e25ad2fa9d1ed987.md>)

Recorded evaluation configuration: {"Number of Neurons":"\[356, 388, 413, 80\]","Dropout Rate":"\[0.1, 0, 0, 0\]","Batch Size":"224","Learning Rate":"0.01"}. This record does not assert independent reproduction.

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