# Image Classification on ImageNet-R (Coverage and Set Size Metrics)

Source: [Image Classification on ImageNet-R (Coverage and Set Size Metrics)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-r-coverage-and-set-size-metrics>)

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

Data updated: 2026-05-25T08:03:23.656Z

Evaluation of Image Classification performance on the ImageNet-R dataset, focusing on Coverage (CP) and Set Size metrics.

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-R |
| Metric | Coverage (CPr-value) |
| 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

- [Coverage (CPr-value)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-r-coverage-and-set-size-metrics.md?metric=Coverage%20(CPr-value)>): Higher is better; unit: PERCENT.

- [Coverage (CPavg)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-r-coverage-and-set-size-metrics.md?metric=Coverage%20(CPavg)>): Higher is better; unit: PERCENT.

- [Coverage (CP)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-r-coverage-and-set-size-metrics.md?metric=Coverage%20(CP)>): Higher is better; unit: PERCENT.

- [Set Size (CPr-value)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-r-coverage-and-set-size-metrics.md?metric=Set%20Size%20(CPr-value)>): Higher is better; unit: SCALAR.

- [Set Size (CPavg)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-r-coverage-and-set-size-metrics.md?metric=Set%20Size%20(CPavg)>): Higher is better; unit: SCALAR.

- [Set Size (CP)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-r-coverage-and-set-size-metrics.md?metric=Set%20Size%20(CP)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Coverage (CPr-value) | Result date | Report paper |
| --- | --- | --- | --- |
| CPr-value | 95.1 | Not recorded | 6a13d7916f71c5ae7dc9e945 |

### CPr-value

Coverage (CPr-value): 95.1. Result ID: 6a140235fbc373592c0afdba.

[Reporting paper](<https://www.sota2.com/research/paper/6a13d7916f71c5ae7dc9e945.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a13d7916f71c5ae7dc9e945.md>)

Recorded evaluation configuration: {"Model":"CLIP","alpha":"0.05"}. This record does not assert independent reproduction.

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