# Image Classification on CIFAR-100 (test) (Including GPU Hours)

Source: [Image Classification on CIFAR-100 (test) (Including GPU Hours)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-including-gpu-hours>)

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

Data updated: 2026-02-26T06:06:14.823Z

Evaluation of Image Classification performance on the CIFAR-100 test set, reporting the Test Error rate alongside resource consumption metrics like GPU Hours.

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 | Test Error |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [Test Error](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-including-gpu-hours.md?metric=Test%20Error>): Lower is better; unit: PERCENT.

- [GPU Hours](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-including-gpu-hours.md?metric=GPU%20Hours>): Lower is better; unit: TIME.

## Recorded results

| Method | Test Error | Result date | Report paper |
| --- | --- | --- | --- |
| AutoAugment | 10.7 | Not recorded | 68fa65bc1e209131cea0c00f |
| Population Based Augmentation | 10.9 | Not recorded | 68fa65bc1e209131cea0c00f |
| Previous Best | 12.2 | Not recorded | 68fa65bc1e209131cea0c00f |

### AutoAugment

Test Error: 10.7. Result ID: 698cc47b8b517eb4331c9ba7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65bc1e209131cea0c00f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a51e209131cea0b94a.md>)

Recorded evaluation configuration: {"policy\_transfer":"learned on CIFAR-10"}. This record does not assert independent reproduction.

### Population Based Augmentation

Test Error: 10.9. Result ID: 698cc47b8b517eb4331c9ba8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65bc1e209131cea0c00f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65bc1e209131cea0c00f.md>)

[Implementation](<https://github.com/arcelien/pba>)

Recorded evaluation configuration: {"policy\_transfer":"learned on CIFAR-10","GPU Type":"Titan XP"}. This record does not assert independent reproduction.

### Previous Best

Test Error: 12.2. Result ID: 698cc47b8b517eb4331c9ba6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65bc1e209131cea0c00f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a51e209131cea0b94a.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.
