# Image Classification on FashionMNIST-10 (test)

Source: [Image Classification on FashionMNIST-10 (test)](<https://www.sota2.com/research/sota/image-classification-on-fashionmnist-10-test>)

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

Data updated: 2026-02-26T06:06:10.861Z

Evaluation of Image Classification performance on the test split of the FashionMNIST-10 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) | FashionMNIST-10 (test) |
| Metric | Test Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Test Accuracy](<https://www.sota2.com/research/sota/image-classification-on-fashionmnist-10-test.md?metric=Test%20Accuracy>): Higher is better; unit: PERCENT.

- [Residual Value](<https://www.sota2.com/research/sota/image-classification-on-fashionmnist-10-test.md?metric=Residual%20Value>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Test Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| IMPLICIT solver | 72.11 | Not recorded | 68fa48681e209131ce92f758 |
| DIRECT solver - 10 layers | 71.83 | Not recorded | 68fa48681e209131ce92f758 |
| IMPLICIT+WARMUP solver | 71.17 | Not recorded | 68fa48681e209131ce92f758 |
| DIRECT solver - 1 layers | 71.05 | Not recorded | 68fa48681e209131ce92f758 |
| DIRECT solver - 5 layers | 70.87 | Not recorded | 68fa48681e209131ce92f758 |
| DIRECT solver - 2 layers | 70.81 | Not recorded | 68fa48681e209131ce92f758 |

### IMPLICIT solver

Test Accuracy: 72.11. Result ID: 698b9e5f7a967eddb7701413.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Implementation](<https://github.com/martaskrt/qdeq>)

Recorded evaluation configuration: {"Memory (MB)":27.3,"Runtime (sec)":6424.67}. This record does not assert independent reproduction.

### DIRECT solver - 10 layers

Test Accuracy: 71.83. Result ID: 698b9e5f7a967eddb7701415.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Implementation](<https://github.com/martaskrt/qdeq>)

Recorded evaluation configuration: {"Memory (MB)":1233.3,"Runtime (sec)":11651.96}. This record does not assert independent reproduction.

### IMPLICIT+WARMUP solver

Test Accuracy: 71.17. Result ID: 698b9e5f7a967eddb7701414.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Implementation](<https://github.com/martaskrt/qdeq>)

Recorded evaluation configuration: {"Memory (MB)":27.3,"Runtime (sec)":7240.35}. This record does not assert independent reproduction.

### DIRECT solver - 1 layers

Test Accuracy: 71.05. Result ID: 698b9e5f7a967eddb7701418.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Implementation](<https://github.com/martaskrt/qdeq>)

Recorded evaluation configuration: {"Memory (MB)":14.5,"Runtime (sec)":3382.09}. This record does not assert independent reproduction.

### DIRECT solver - 5 layers

Test Accuracy: 70.87. Result ID: 698b9e5f7a967eddb7701416.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Implementation](<https://github.com/martaskrt/qdeq>)

Recorded evaluation configuration: {"Memory (MB)":62.9,"Runtime (sec)":6894.5}. This record does not assert independent reproduction.

### DIRECT solver - 2 layers

Test Accuracy: 70.81. Result ID: 698b9e5f7a967eddb7701417.

[Reporting paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa48681e209131ce92f758.md>)

[Implementation](<https://github.com/martaskrt/qdeq>)

Recorded evaluation configuration: {"Memory (MB)":26.6,"Runtime (sec)":4135.23}. This record does not assert independent reproduction.

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