# Image Classification on MNIST (test) (Calibration Metrics)

Source: [Image Classification on MNIST (test) (Calibration Metrics)](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-calibration-metrics>)

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

Data updated: 2026-05-18T07:17:47.482Z

Standard evaluation of Image Classification performance on the MNIST test set, reporting accuracy alongside key model calibration metrics such as Expected Calibration Error (ECE), Brier Score, and Negative Log Likelihood (NLL).

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 | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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-test-calibration-metrics.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [NLL](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-calibration-metrics.md?metric=NLL>): Lower is better; unit: SCALAR.

- [Brier Score](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-calibration-metrics.md?metric=Brier%20Score>): Lower is better; unit: SCALAR.

- [ECE](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-calibration-metrics.md?metric=ECE>): Lower is better; unit: SCALAR.

- [MCE](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-calibration-metrics.md?metric=MCE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| RLA | 95.3 | Not recorded | 6a0a9d15dbc836b87d82b40d |
| DIMS | 95 | Not recorded | 6a0a9d15dbc836b87d82b40d |
| LINLA | 86 | Not recorded | 6a0a9d15dbc836b87d82b40d |
| LA | 56.4 | Not recorded | 6a0a9d15dbc836b87d82b40d |

### RLA

Accuracy: 95.3. Result ID: 6a0abbfc47f34ce924f067a5.

[Reporting paper](<https://www.sota2.com/research/paper/6a0a9d15dbc836b87d82b40d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6faf1e209131cea46e23.md>)

Recorded evaluation configuration: {"Hessian approximation type":"low-rank","Backbone":"LeNet","Number of parameter samples":"100"}. This record does not assert independent reproduction.

### DIMS

Accuracy: 95. Result ID: 6a0abbfc47f34ce924f067a6.

[Reporting paper](<https://www.sota2.com/research/paper/6a0a9d15dbc836b87d82b40d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0a9d15dbc836b87d82b40d.md>)

Recorded evaluation configuration: {"Hessian approximation type":"low-rank","Backbone":"LeNet","Number of parameter samples":"100","friction coefficient η0":"0.1"}. This record does not assert independent reproduction.

### LINLA

Accuracy: 86. Result ID: 6a0abbfc47f34ce924f067a4.

[Reporting paper](<https://www.sota2.com/research/paper/6a0a9d15dbc836b87d82b40d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69541e209131cea2192f.md>)

Recorded evaluation configuration: {"Hessian approximation type":"low-rank","Backbone":"LeNet","Number of parameter samples":"100"}. This record does not assert independent reproduction.

### LA

Accuracy: 56.4. Result ID: 6a0abbfc47f34ce924f067a3.

[Reporting paper](<https://www.sota2.com/research/paper/6a0a9d15dbc836b87d82b40d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6faf1e209131cea46e23.md>)

Recorded evaluation configuration: {"Hessian approximation type":"low-rank","Backbone":"LeNet","Number of parameter samples":"100"}. This record does not assert independent reproduction.

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