# Image Classification on MNIST Digits 61 (test)

Source: [Image Classification on MNIST Digits 61 (test)](<https://www.sota2.com/research/sota/image-classification-on-mnist-digits-61-test>)

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

Data updated: 2026-02-26T05:27:07.314Z

Evaluation of Image Classification performance on the test split of the MNIST Digits 61 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) | MNIST Digits 61 (test) |
| Metric | 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-mnist-digits-61-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Eff.-CapsNet | 99.84 | Not recorded | 68fa48ea1e209131ce933310 |
| CTM-8000 | 99.4 | Not recorded | 68fa48ea1e209131ce933310 |
| ConvPMM | 99.1 | Not recorded | 68fa48ea1e209131ce933310 |
| CTM-250 | 98.82 | Not recorded | 68fa48ea1e209131ce933310 |
| GECCO | 98.04 | Not recorded | 68fa48ea1e209131ce933310 |
| PMM | 97.38 | Not recorded | 68fa48ea1e209131ce933310 |
| DNN-5 | 97.2 | Not recorded | 68fa48ea1e209131ce933310 |
| DNN-3 | 97 | Not recorded | 68fa48ea1e209131ce933310 |
| DNN-2 | 96.5 | Not recorded | 68fa48ea1e209131ce933310 |

### Eff.-CapsNet

Accuracy: 99.84. Result ID: 698b9ed87a967eddb7701780.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48ea1e209131ce933310.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7e1e209131cea2e926.md>)

[Implementation](<https://github.com/EscVM/Efficient-CapsNet>)

Recorded evaluation configuration: {"float":161824}. This record does not assert independent reproduction.

### CTM-8000

Accuracy: 99.4. Result ID: 698b9ed87a967eddb770177f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48ea1e209131ce933310.md>)

Recorded evaluation configuration: {"float":527250}. This record does not assert independent reproduction.

### ConvPMM

Accuracy: 99.1. Result ID: 698b9ed87a967eddb7701779.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48ea1e209131ce933310.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa48ea1e209131ce933310.md>)

Recorded evaluation configuration: {"float":129416}. This record does not assert independent reproduction.

### CTM-250

Accuracy: 98.82. Result ID: 698b9ed87a967eddb770177e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48ea1e209131ce933310.md>)

Recorded evaluation configuration: {"float":31750}. This record does not assert independent reproduction.

### GECCO

Accuracy: 98.04. Result ID: 698b9ed87a967eddb770177d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48ea1e209131ce933310.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73d51e209131cea5e63d.md>)

[Implementation](<https://github.com/GECCOProject/GECCO>)

Recorded evaluation configuration: {"float":"~19000"}. This record does not assert independent reproduction.

### PMM

Accuracy: 97.38. Result ID: 698b9ed87a967eddb7701778.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48ea1e209131ce933310.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa48ea1e209131ce933310.md>)

Recorded evaluation configuration: {"float":4990}. This record does not assert independent reproduction.

### DNN-5

Accuracy: 97.2. Result ID: 698b9ed87a967eddb770177c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48ea1e209131ce933310.md>)

Recorded evaluation configuration: {"float":"~575050"}. This record does not assert independent reproduction.

### DNN-3

Accuracy: 97. Result ID: 698b9ed87a967eddb770177b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48ea1e209131ce933310.md>)

Recorded evaluation configuration: {"float":"~386718"}. This record does not assert independent reproduction.

### DNN-2

Accuracy: 96.5. Result ID: 698b9ed87a967eddb770177a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48ea1e209131ce933310.md>)

Recorded evaluation configuration: {"float":"~311650"}. This record does not assert independent reproduction.

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