# Image Classification on ImageNet-1K (test) (Accuracy & FLOPs)

Source: [Image Classification on ImageNet-1K (test) (Accuracy & FLOPs)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-test-accuracy-and-flops>)

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

Data updated: 2026-03-30T07:14:08.016Z

Evaluation of Image Classification performance on the test split of the ImageNet-1K dataset, reporting standard Accuracy alongside associated computational cost (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) | ImageNet-1K (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-imagenet-1k-test-accuracy-and-flops.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [FLOPs (x10^16)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-test-accuracy-and-flops.md?metric=FLOPs%20(x10%5E16)>): Lower is better; unit: SIZE.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PruneFuse | 74 | Not recorded | 69ca035f0636e5bf4afc91df |
| PruneFuse | 73.86 | Not recorded | 69ca035f0636e5bf4afc91df |
| PruneFuse | 73.84 | Not recorded | 69ca035f0636e5bf4afc91df |
| PruneFuse | 73.64 | Not recorded | 69ca035f0636e5bf4afc91df |
| Baseline (AL) | 73.56 | Not recorded | 69ca035f0636e5bf4afc91df |

### PruneFuse

Accuracy: 74. Result ID: 69ca22b147f34ce924b25676.

[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":"4.59 M","Pruning ratio (p)":"0.6","Backbone":"ResNet-50","Sampling Strategy":"Least-Confidence"}. This record does not assert independent reproduction.

### PruneFuse

Accuracy: 73.86. Result ID: 69ca22b147f34ce924b25675.

[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":"6.91 M","Pruning ratio (p)":"0.5","Backbone":"ResNet-50","Sampling Strategy":"Least-Confidence"}. This record does not assert independent reproduction.

### PruneFuse

Accuracy: 73.84. Result ID: 69ca22b147f34ce924b25677.

[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":"2.74 M","Pruning ratio (p)":"0.7","Backbone":"ResNet-50","Sampling Strategy":"Least-Confidence"}. This record does not assert independent reproduction.

### PruneFuse

Accuracy: 73.64. Result ID: 69ca22b147f34ce924b25678.

[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":"1.35 M","Pruning ratio (p)":"0.8","Backbone":"ResNet-50","Sampling Strategy":"Least-Confidence"}. This record does not assert independent reproduction.

### Baseline (AL)

Accuracy: 73.56. Result ID: 69ca22b147f34ce924b25674.

[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":"25.5 M","Backbone":"ResNet-50","Sampling Strategy":"Least-Confidence"}. This record does not assert independent reproduction.

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