# Image Classification on CIFAR-100 (test) (NLL, ACC, ECE)

Source: [Image Classification on CIFAR-100 (test) (NLL, ACC, ECE)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-nll-acc-ece>)

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

Data updated: 2026-02-26T05:53:14.523Z

Evaluation of standard Image Classification performance on the CIFAR-100 test set, reporting accuracy, 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) | CIFAR-100 (test) |
| Metric | NLL |
| Unit | SCALAR |
| Direction | Lower 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

- [NLL](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-nll-acc-ece.md?metric=NLL>): Lower is better; unit: SCALAR.

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-nll-acc-ece.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [ECE](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-nll-acc-ece.md?metric=ECE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | NLL | Result date | Report paper |
| --- | --- | --- | --- |
| CIBER | 0.9193 | Not recorded | 68fa72211e209131cea54b2c |
| SGLD | 0.9699 | Not recorded | 68fa72211e209131cea54b2c |
| KFAC | 1.1915 | Not recorded | 68fa72211e209131cea54b2c |
| SWA | 1.278 | Not recorded | 68fa72211e209131cea54b2c |
| SWAG | 1.2785 | Not recorded | 68fa72211e209131cea54b2c |
| SGD | 1.7308 | Not recorded | 68fa72211e209131cea54b2c |

### CIBER

NLL: 0.9193. Result ID: 699207543a6c3148490c2324.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b2c.md>)

[Implementation](<https://github.com/UCLA-StarAI/CIBER>)

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

### SGLD

NLL: 0.9699. Result ID: 699207543a6c3148490c2328.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b2c.md>)

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

### KFAC

NLL: 1.1915. Result ID: 699207543a6c3148490c2329.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b2c.md>)

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

### SWA

NLL: 1.278. Result ID: 699207543a6c3148490c2327.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65651e209131cea09f96.md>)

[Implementation](<https://github.com/timgaripov/swa>)

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

### SWAG

NLL: 1.2785. Result ID: 699207543a6c3148490c2325.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b2c.md>)

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

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

### SGD

NLL: 1.7308. Result ID: 699207543a6c3148490c2326.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72211e209131cea54b2c.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.