# Image Classification on CIFAR-10 (test) (Accuracy, Calibration, and Uncertainty)

Source: [Image Classification on CIFAR-10 (test) (Accuracy, Calibration, and Uncertainty)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-calibration-and-uncertainty>)

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

Data updated: 2026-02-26T05:32:05.796Z

Evaluation of Image Classification model performance on the CIFAR-10 test set, covering standard accuracy, calibration error (ECE, Brier), and uncertainty quantification metrics (AUROC, AURC).

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-10 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-calibration-and-uncertainty.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [AURC](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-calibration-and-uncertainty.md?metric=AURC>): Higher is better; unit: SCALAR.

- [AUROC](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-calibration-and-uncertainty.md?metric=AUROC>): Higher is better; unit: PERCENT.

- [FPR@95](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-calibration-and-uncertainty.md?metric=FPR%4095>): Lower is better; unit: PERCENT.

- [ECE](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-calibration-and-uncertainty.md?metric=ECE>): Lower is better; unit: PERCENT.

- [NLL](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-calibration-and-uncertainty.md?metric=NLL>): Lower is better; unit: SCALAR.

- [Brier Score](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-calibration-and-uncertainty.md?metric=Brier%20Score>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DIRECTOR | 87.06 | Not recorded | 698abc44c97a0b3e3b5de592 |
| DIRECTOR | 86.51 | Not recorded | 698abc44c97a0b3e3b5de592 |
| DIRECTOR | 85.67 | Not recorded | 698abc44c97a0b3e3b5de592 |
| KEP-1/7 | 84.52 | Not recorded | 698abc44c97a0b3e3b5de592 |
| ViT | 83.84 | Not recorded | 698abc44c97a0b3e3b5de592 |
| KEP-7/7 | 82.68 | Not recorded | 698abc44c97a0b3e3b5de592 |

### DIRECTOR

Accuracy: 87.06. Result ID: 6998d2f05698665ec436a3fc.

[Reporting paper](<https://www.sota2.com/research/paper/698abc44c97a0b3e3b5de592.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc44c97a0b3e3b5de592.md>)

Recorded evaluation configuration: {"base\_architecture":"KEP-7/7"}. This record does not assert independent reproduction.

### DIRECTOR

Accuracy: 86.51. Result ID: 6998d2f05698665ec436a3fa.

[Reporting paper](<https://www.sota2.com/research/paper/698abc44c97a0b3e3b5de592.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc44c97a0b3e3b5de592.md>)

Recorded evaluation configuration: {"base\_architecture":"KEP-1/7"}. This record does not assert independent reproduction.

### DIRECTOR

Accuracy: 85.67. Result ID: 6998d2f05698665ec436a3f8.

[Reporting paper](<https://www.sota2.com/research/paper/698abc44c97a0b3e3b5de592.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc44c97a0b3e3b5de592.md>)

Recorded evaluation configuration: {"base\_architecture":"ViT"}. This record does not assert independent reproduction.

### KEP-1/7

Accuracy: 84.52. Result ID: 6998d2f05698665ec436a3f9.

[Reporting paper](<https://www.sota2.com/research/paper/698abc44c97a0b3e3b5de592.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa736c1e209131cea5c67b.md>)

Recorded evaluation configuration: {"architecture":"KEP-1/7"}. This record does not assert independent reproduction.

### ViT

Accuracy: 83.84. Result ID: 6998d2f05698665ec436a3f7.

[Reporting paper](<https://www.sota2.com/research/paper/698abc44c97a0b3e3b5de592.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"architecture":"ViT"}. This record does not assert independent reproduction.

### KEP-7/7

Accuracy: 82.68. Result ID: 6998d2f05698665ec436a3fb.

[Reporting paper](<https://www.sota2.com/research/paper/698abc44c97a0b3e3b5de592.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa736c1e209131cea5c67b.md>)

Recorded evaluation configuration: {"architecture":"KEP-7/7"}. This record does not assert independent reproduction.

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