# Image Classification on CIFAR-10 (test) (Accuracy vs GELU Delta)

Source: [Image Classification on CIFAR-10 (test) (Accuracy vs GELU Delta)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-vs-gelu-delta>)

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

Data updated: 2026-04-24T08:37:27.462Z

Evaluation of standard Image Classification model performance on the CIFAR-10 test set, reporting classification accuracy and the delta comparison against the GELU activation function.

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 | 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

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

- [Accuracy Delta (vs GELU)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-vs-gelu-delta.md?metric=Accuracy%20Delta%20(vs%20GELU)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SE-GEM | 92.51 | Not recorded | 69eaf93c55a3c32af89f8b2e |
| GELU | 92.44 | Not recorded | 69eaf93c55a3c32af89f8b2e |
| ReLU | 91.33 | Not recorded | 69eaf93c55a3c32af89f8b2e |

### SE-GEM

Accuracy: 92.51. Result ID: 69eb2bb447f34ce924d377a5.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf93c55a3c32af89f8b2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69eaf93c55a3c32af89f8b2e.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-56","Epsilon (ε)":"10⁻⁴"}. This record does not assert independent reproduction.

### GELU

Accuracy: 92.44. Result ID: 69eb2bb447f34ce924d377a6.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf93c55a3c32af89f8b2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fa11e209131cea46c57.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-56"}. This record does not assert independent reproduction.

### ReLU

Accuracy: 91.33. Result ID: 69eb2bb447f34ce924d377a7.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf93c55a3c32af89f8b2e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65571e209131cea09dfc.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-56"}. This record does not assert independent reproduction.

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