# Image Classification on MNIST (NLL and ECE)

Source: [Image Classification on MNIST (NLL and ECE)](<https://www.sota2.com/research/sota/image-classification-on-mnist-nll-and-ece>)

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

Data updated: 2026-02-26T05:53:16.310Z

Evaluation of Image Classification performance on the MNIST dataset, focusing on calibration metrics including Negative Log-Likelihood (NLL) and Expected Calibration Error (ECE).

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 |
| Metric | NLL |
| Unit | SCALAR |
| Direction | Lower 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

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

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

## Recorded results

| Method | NLL | Result date | Report paper |
| --- | --- | --- | --- |
| MetricBNN | 0.12 | Not recorded | 692e7317d6b0dd3342932757 |
| ESPRO | 0.15 | Not recorded | 692e7317d6b0dd3342932757 |
| ENSEMBLES | 0.17 | Not recorded | 692e7317d6b0dd3342932757 |
| SWAG | 0.24 | Not recorded | 692e7317d6b0dd3342932757 |
| Riem Lin LA | 0.62 | Not recorded | 692e7317d6b0dd3342932757 |
| Lin LA | 0.96 | Not recorded | 692e7317d6b0dd3342932757 |
| Riem LA | 1.11 | Not recorded | 692e7317d6b0dd3342932757 |
| LA LowRank | 1.35 | Not recorded | 692e7317d6b0dd3342932757 |
| SGLD | 1.6 | Not recorded | 692e7317d6b0dd3342932757 |
| LA GN | 2.42 | Not recorded | 692e7317d6b0dd3342932757 |

### MetricBNN

NLL: 0.12. Result ID: 699996625698665ec40a4b40.

[Reporting paper](<https://www.sota2.com/research/paper/692e7317d6b0dd3342932757.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692e7317d6b0dd3342932757.md>)

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

### ESPRO

NLL: 0.15. Result ID: 699996625698665ec40a4b3e.

[Reporting paper](<https://www.sota2.com/research/paper/692e7317d6b0dd3342932757.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b471e209131cea2d3e3.md>)

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

### ENSEMBLES

NLL: 0.17. Result ID: 699996625698665ec40a4b3c.

[Reporting paper](<https://www.sota2.com/research/paper/692e7317d6b0dd3342932757.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63bc1e209131cea0084f.md>)

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

### SWAG

NLL: 0.24. Result ID: 699996625698665ec40a4b3f.

[Reporting paper](<https://www.sota2.com/research/paper/692e7317d6b0dd3342932757.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e71e209131cea130c6.md>)

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

### Riem Lin LA

NLL: 0.62. Result ID: 699996625698665ec40a4b3b.

[Reporting paper](<https://www.sota2.com/research/paper/692e7317d6b0dd3342932757.md>)

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

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

### Lin LA

NLL: 0.96. Result ID: 699996625698665ec40a4b3a.

[Reporting paper](<https://www.sota2.com/research/paper/692e7317d6b0dd3342932757.md>)

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

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

### Riem LA

NLL: 1.11. Result ID: 699996625698665ec40a4b39.

[Reporting paper](<https://www.sota2.com/research/paper/692e7317d6b0dd3342932757.md>)

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

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

### LA LowRank

NLL: 1.35. Result ID: 699996625698665ec40a4b38.

[Reporting paper](<https://www.sota2.com/research/paper/692e7317d6b0dd3342932757.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfe1e209131cea31830.md>)

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

### SGLD

NLL: 1.6. Result ID: 699996625698665ec40a4b3d.

[Reporting paper](<https://www.sota2.com/research/paper/692e7317d6b0dd3342932757.md>)

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

### LA GN

NLL: 2.42. Result ID: 699996625698665ec40a4b37.

[Reporting paper](<https://www.sota2.com/research/paper/692e7317d6b0dd3342932757.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfe1e209131cea31830.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.