# Image Classification on Permuted MNIST (p1, p2, p3) (test)

Source: [Image Classification on Permuted MNIST (p1, p2, p3) (test)](<https://www.sota2.com/research/sota/image-classification-on-permuted-mnist-p1-p2-p3-test>)

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

Data updated: 2026-03-31T07:10:54.733Z

Evaluation of standard Image Classification accuracy across three distinct permutations (p1, p2, p3) of the Permuted MNIST (pMNIST) dataset on the test split.

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) | Permuted MNIST p1, p2, p3 (test) |
| Metric | Task 1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Task 1 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-permuted-mnist-p1-p2-p3-test.md?metric=Task%201%20Accuracy>): Higher is better; unit: PERCENT.

- [Task 2 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-permuted-mnist-p1-p2-p3-test.md?metric=Task%202%20Accuracy>): Higher is better; unit: PERCENT.

- [Task 3 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-permuted-mnist-p1-p2-p3-test.md?metric=Task%203%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Task 1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SI | 92.8 | Not recorded | 69cb55170636e5bf4afc9ed5 |
| OGD | 79.3 | Not recorded | 69cb55170636e5bf4afc9ed5 |
| SFAO | 76 | Not recorded | 69cb55170636e5bf4afc9ed5 |
| SGD | 75.7 | Not recorded | 69cb55170636e5bf4afc9ed5 |
| EWC | 73 | Not recorded | 69cb55170636e5bf4afc9ed5 |

### SI

Task 1 Accuracy: 92.8. Result ID: 69cb737c47f34ce924b34d8e.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55170636e5bf4afc9ed5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5ed01e209131ce9e565c.md>)

Recorded evaluation configuration: {"Architecture":"Simple MLP"}. This record does not assert independent reproduction.

### OGD

Task 1 Accuracy: 79.3. Result ID: 69cb737c47f34ce924b34d8f.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55170636e5bf4afc9ed5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa667d1e209131cea10916.md>)

Recorded evaluation configuration: {"Architecture":"Simple MLP"}. This record does not assert independent reproduction.

### SFAO

Task 1 Accuracy: 76. Result ID: 69cb737c47f34ce924b34d90.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55170636e5bf4afc9ed5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb55170636e5bf4afc9ed5.md>)

Recorded evaluation configuration: {"Architecture":"Simple MLP"}. This record does not assert independent reproduction.

### SGD

Task 1 Accuracy: 75.7. Result ID: 69cb737c47f34ce924b34d8c.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55170636e5bf4afc9ed5.md>)

Recorded evaluation configuration: {"Architecture":"Simple MLP"}. This record does not assert independent reproduction.

### EWC

Task 1 Accuracy: 73. Result ID: 69cb737c47f34ce924b34d8d.

[Reporting paper](<https://www.sota2.com/research/paper/69cb55170636e5bf4afc9ed5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3555e.md>)

Recorded evaluation configuration: {"Architecture":"Simple MLP"}. This record does not assert independent reproduction.

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