# Image Classification on CIFAR10 (NLL and ECE)

Source: [Image Classification on CIFAR10 (NLL and ECE)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-nll-and-ece>)

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

Data updated: 2026-02-26T05:53:16.341Z

Evaluation of Image Classification performance on the CIFAR-10 dataset, reporting 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) | CIFAR10 |
| 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-cifar10-nll-and-ece.md?metric=NLL>): Lower is better; unit: SCALAR.

- [ECE](<https://www.sota2.com/research/sota/image-classification-on-cifar10-nll-and-ece.md?metric=ECE>): Lower is better; unit: PERCENT.

## Recorded results

| Method | NLL | Result date | Report paper |
| --- | --- | --- | --- |
| MetricBNN | 0.7 | Not recorded | 692e7317d6b0dd3342932757 |
| SGLD | 0.78 | Not recorded | 692e7317d6b0dd3342932757 |
| Riem Lin LA | 0.83 | Not recorded | 692e7317d6b0dd3342932757 |
| Riem LA | 0.84 | Not recorded | 692e7317d6b0dd3342932757 |
| ESPRO | 0.84 | Not recorded | 692e7317d6b0dd3342932757 |
| ENSEMBLES | 1.55 | Not recorded | 692e7317d6b0dd3342932757 |
| Lin LA | 1.93 | Not recorded | 692e7317d6b0dd3342932757 |
| SWAG | 1.97 | Not recorded | 692e7317d6b0dd3342932757 |
| LA LowRank | 2.19 | Not recorded | 692e7317d6b0dd3342932757 |
| LA GN | 2.29 | Not recorded | 692e7317d6b0dd3342932757 |

### MetricBNN

NLL: 0.7. Result ID: 699996625698665ec40a4b54.

[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.

### SGLD

NLL: 0.78. Result ID: 699996625698665ec40a4b51.

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

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

### Riem Lin LA

NLL: 0.83. Result ID: 699996625698665ec40a4b4f.

[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.

### Riem LA

NLL: 0.84. Result ID: 699996625698665ec40a4b4d.

[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.

### ESPRO

NLL: 0.84. Result ID: 699996625698665ec40a4b52.

[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: 1.55. Result ID: 699996625698665ec40a4b50.

[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.

### Lin LA

NLL: 1.93. Result ID: 699996625698665ec40a4b4e.

[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.

### SWAG

NLL: 1.97. Result ID: 699996625698665ec40a4b53.

[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.

### LA LowRank

NLL: 2.19. Result ID: 699996625698665ec40a4b4c.

[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.

### LA GN

NLL: 2.29. Result ID: 699996625698665ec40a4b4b.

[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.