# Image Classification on CIFAR-100 (test) (Accuracy and FLOPs)

Source: [Image Classification on CIFAR-100 (test) (Accuracy and FLOPs)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-accuracy-and-flops>)

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

Data updated: 2026-03-30T07:14:07.954Z

Evaluation of Image Classification performance on the CIFAR-100 test set, reporting standard accuracy and computational cost measured in FLOPs.

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 | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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-100-test-accuracy-and-flops.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Computation (x10^16 FLOPs)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-accuracy-and-flops.md?metric=Computation%20(x10%5E16%20FLOPs)>): Lower is better; unit: SIZE.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PruneFuse | 67.87 | Not recorded | 69ca035f0636e5bf4afc91df |
| PruneFuse | 66.89 | Not recorded | 69ca035f0636e5bf4afc91df |
| PruneFuse | 66.84 | Not recorded | 69ca035f0636e5bf4afc91df |
| Baseline (AL) | 66.72 | Not recorded | 69ca035f0636e5bf4afc91df |
| PruneFuse | 65.85 | Not recorded | 69ca035f0636e5bf4afc91df |

### PruneFuse

Accuracy: 67.87. Result ID: 69ca22b147f34ce924b2566b.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035f0636e5bf4afc91df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ca035f0636e5bf4afc91df.md>)

Recorded evaluation configuration: {"Budget (b)":"50%","Params":"0.22 M","Pruning ratio (p)":"0.5","Backbone":"ResNet-56","Sampling Strategy":"Least-Confidence"}. This record does not assert independent reproduction.

### PruneFuse

Accuracy: 66.89. Result ID: 69ca22b147f34ce924b2566c.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035f0636e5bf4afc91df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ca035f0636e5bf4afc91df.md>)

Recorded evaluation configuration: {"Budget (b)":"50%","Params":"0.14 M","Pruning ratio (p)":"0.6","Backbone":"ResNet-56","Sampling Strategy":"Least-Confidence"}. This record does not assert independent reproduction.

### PruneFuse

Accuracy: 66.84. Result ID: 69ca22b147f34ce924b2566d.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035f0636e5bf4afc91df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ca035f0636e5bf4afc91df.md>)

Recorded evaluation configuration: {"Budget (b)":"50%","Params":"0.08 M","Pruning ratio (p)":"0.7","Backbone":"ResNet-56","Sampling Strategy":"Least-Confidence"}. This record does not assert independent reproduction.

### Baseline (AL)

Accuracy: 66.72. Result ID: 69ca22b147f34ce924b2566a.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035f0636e5bf4afc91df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa689c1e209131cea1d024.md>)

Recorded evaluation configuration: {"Budget (b)":"50%","Params":"0.86 M","Backbone":"ResNet-56","Sampling Strategy":"Least-Confidence"}. This record does not assert independent reproduction.

### PruneFuse

Accuracy: 65.85. Result ID: 69ca22b147f34ce924b2566e.

[Reporting paper](<https://www.sota2.com/research/paper/69ca035f0636e5bf4afc91df.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ca035f0636e5bf4afc91df.md>)

Recorded evaluation configuration: {"Budget (b)":"50%","Params":"0.04 M","Pruning ratio (p)":"0.8","Backbone":"ResNet-56","Sampling Strategy":"Least-Confidence"}. This record does not assert independent reproduction.

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