# Image Classification on CIFAR-10 (Accuracy, Time, Power, Energy)

Source: [Image Classification on CIFAR-10 (Accuracy, Time, Power, Energy)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy-time-power-energy>)

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

Data updated: 2026-03-17T10:07:10.952Z

Evaluation of Image Classification performance on the CIFAR-10 dataset, reporting standard accuracy alongside hardware efficiency metrics including inference time, power consumption, and total energy usage.

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 | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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-accuracy-time-power-energy.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Inference Time (ms)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy-time-power-energy.md?metric=Inference%20Time%20(ms)>): Lower is better; unit: TIME.

- [Average Power (W)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy-time-power-energy.md?metric=Average%20Power%20(W)>): Lower is better; unit: OTHER.

- [Total Energy (mJ)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy-time-power-energy.md?metric=Total%20Energy%20(mJ)>): Lower is better; unit: OTHER.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| QDSNN | 78 | Not recorded | 69b8e0160636e5bf4afbeab9 |
| SNN | 77.01 | Not recorded | 69b8e0160636e5bf4afbeab9 |
| QSNN | 74.3 | Not recorded | 69b8e0160636e5bf4afbeab9 |
| QDSNN | 64.8 | Not recorded | 69b8e0160636e5bf4afbeab9 |

### QDSNN

Accuracy: 78. Result ID: 69b927be47f34ce924a25fd3.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0160636e5bf4afbeab9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0160636e5bf4afbeab9.md>)

Recorded evaluation configuration: {"Architecture":"AlexNet","Thresholds":"0.6/0.7"}. This record does not assert independent reproduction.

### SNN

Accuracy: 77.01. Result ID: 69b927be47f34ce924a25fd0.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0160636e5bf4afbeab9.md>)

Recorded evaluation configuration: {"Architecture":"AlexNet","Timesteps (T)":"32"}. This record does not assert independent reproduction.

### QSNN

Accuracy: 74.3. Result ID: 69b927be47f34ce924a25fd1.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0160636e5bf4afbeab9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ea1e209131cea6fed7.md>)

Recorded evaluation configuration: {"Architecture":"AlexNet","Timesteps (T)":"4"}. This record does not assert independent reproduction.

### QDSNN

Accuracy: 64.8. Result ID: 69b927be47f34ce924a25fd2.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0160636e5bf4afbeab9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0160636e5bf4afbeab9.md>)

Recorded evaluation configuration: {"Architecture":"AlexNet","Thresholds":"0.2/0.4"}. This record does not assert independent reproduction.

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