# Image Classification on CIFAR-10 (Top-1 Error Rate)

Source: [Image Classification on CIFAR-10 (Top-1 Error Rate)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-top-1-error-rate>)

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

Data updated: 2026-02-26T06:07:18.976Z

Evaluation of standard Image Classification performance on the CIFAR-10 dataset, reporting the Top-1 error rate.

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 |
| Metric | Top-1 Error Rate |
| Unit | PERCENT |
| 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

- [Top-1 Error Rate](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-top-1-error-rate.md?metric=Top-1%20Error%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Error Rate | Result date | Report paper |
| --- | --- | --- | --- |
| EfficientNet-L2 | 30 | Not recorded | 68fa69d81e209131cea248fb |
| EfficientNet-L2 | 34 | Not recorded | 68fa69d81e209131cea248fb |
| BiT-L | 63 | Not recorded | 68fa69d81e209131cea248fb |
| EfficientNet-b7 | 88 | Not recorded | 68fa69d81e209131cea248fb |
| EfficientNet-b7 | 95 | Not recorded | 68fa69d81e209131cea248fb |
| Gpipe | 100 | Not recorded | 68fa69d81e209131cea248fb |

### EfficientNet-L2

Top-1 Error Rate: 30. Result ID: 698dee09ffc3901de0999f42.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248fb.md>)

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

Recorded evaluation configuration: {"Backbone":"EfficientNet-L2","SAM Optimization":true,"Pre-training Dataset":"ImageNet plus JFT"}. This record does not assert independent reproduction.

### EfficientNet-L2

Top-1 Error Rate: 34. Result ID: 698dee09ffc3901de0999f43.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248fb.md>)

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

Recorded evaluation configuration: {"Backbone":"EfficientNet-L2","SAM Optimization":false,"Pre-training Dataset":"ImageNet plus JFT"}. This record does not assert independent reproduction.

### BiT-L

Top-1 Error Rate: 63. Result ID: 698dee09ffc3901de0999f44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa677a1e209131cea16a7e.md>)

[Implementation](<https://github.com/tensorflow/tpu/tree/master/models/official/retinanet>)

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

### EfficientNet-b7

Top-1 Error Rate: 88. Result ID: 698dee09ffc3901de0999f3f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248fb.md>)

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

Recorded evaluation configuration: {"Backbone":"EfficientNet-b7","SAM Optimization":true,"Pre-training Dataset":"ImageNet-only"}. This record does not assert independent reproduction.

### EfficientNet-b7

Top-1 Error Rate: 95. Result ID: 698dee09ffc3901de0999f40.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248fb.md>)

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

Recorded evaluation configuration: {"Backbone":"EfficientNet-b7","SAM Optimization":false,"Pre-training Dataset":"ImageNet-only"}. This record does not assert independent reproduction.

### Gpipe

Top-1 Error Rate: 100. Result ID: 698dee09ffc3901de0999f41.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66121e209131cea0e102.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"ImageNet-only"}. This record does not assert independent reproduction.

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