# Sequential Image Classification on pMNIST (average over 3 seeds, val)

Source: [Sequential Image Classification on pMNIST (average over 3 seeds, val)](<https://www.sota2.com/research/sota/sequential-image-classification-on-pmnist-average-over-3-seeds-val>)

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

Data updated: 2026-02-26T06:08:06.394Z

Evaluation of sequential image classification performance on the validation split of the pMNIST dataset, averaged over 3 random seeds.

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 | Sequential Image Classification |
| Dataset (including any stated split) | pMNIST average over 3 seeds (val) |
| Metric | Validation Accuracy |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Validation Accuracy](<https://www.sota2.com/research/sota/sequential-image-classification-on-pmnist-average-over-3-seeds-val.md?metric=Validation%20Accuracy>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Validation Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HiPPO-LegS | 0.9834 | Not recorded | 68fa68a01e209131cea1d397 |
| HiPPO-LagT | 0.9815 | Not recorded | 68fa68a01e209131cea1d397 |
| HiPPO-LegT | 0.98 | Not recorded | 68fa68a01e209131cea1d397 |
| LMU | 0.9708 | Not recorded | 68fa68a01e209131cea1d397 |
| ExpRNN | 0.9467 | Not recorded | 68fa68a01e209131cea1d397 |
| GRU | 0.9304 | Not recorded | 68fa68a01e209131cea1d397 |
| HiPPO-LegT | 0.9175 | Not recorded | 68fa68a01e209131cea1d397 |
| MGU | 0.8937 | Not recorded | 68fa68a01e209131cea1d397 |
| -Rand | 0.6993 | Not recorded | 68fa68a01e209131cea1d397 |
| RNN | 0.5298 | Not recorded | 68fa68a01e209131cea1d397 |

### HiPPO-LegS

Validation Accuracy: 0.9834. Result ID: 698d7a528b517eb43321cf24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Implementation](<https://github.com/HazyResearch/hippo-code>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HiPPO-LagT

Validation Accuracy: 0.9815. Result ID: 698d7a528b517eb43321cf25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Implementation](<https://github.com/HazyResearch/hippo-code>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HiPPO-LegT

Validation Accuracy: 0.98. Result ID: 698d7a528b517eb43321cf26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Implementation](<https://github.com/HazyResearch/hippo-code>)

Recorded evaluation configuration: {"theta":"200"}. This record does not assert independent reproduction.

### LMU

Validation Accuracy: 0.9708. Result ID: 698d7a528b517eb43321cf29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ExpRNN

Validation Accuracy: 0.9467. Result ID: 698d7a528b517eb43321cf2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66661e209131cea101fd.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GRU

Validation Accuracy: 0.9304. Result ID: 698d7a528b517eb43321cf2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa619e1e209131ce9f5331.md>)

[Implementation](<https://github.com/jych/librnn.git>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HiPPO-LegT

Validation Accuracy: 0.9175. Result ID: 698d7a528b517eb43321cf27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Implementation](<https://github.com/HazyResearch/hippo-code>)

Recorded evaluation configuration: {"theta":"20"}. This record does not assert independent reproduction.

### MGU

Validation Accuracy: 0.8937. Result ID: 698d7a528b517eb43321cf2c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### -Rand

Validation Accuracy: 0.6993. Result ID: 698d7a528b517eb43321cf28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

[Implementation](<https://github.com/HazyResearch/hippo-code>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RNN

Validation Accuracy: 0.5298. Result ID: 698d7a528b517eb43321cf2d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68a01e209131cea1d397.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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