# Image Classification on Standard CLIP Evaluation Suite (IN-1K, Caltech, CUB, DTD, ESAT, FLO, SUN, UCF) (test)

Source: [Image Classification on Standard CLIP Evaluation Suite (IN-1K, Caltech, CUB, DTD, ESAT, FLO, SUN, UCF) (test)](<https://www.sota2.com/research/sota/image-classification-on-standard-clip-evaluation-suite-in-1k-caltech-cub-dtd-esat-flo-sun-ucf-test>)

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

Data updated: 2026-02-26T05:46:52.553Z

Evaluation of Image Classification performance across the 8 datasets comprising the Standard CLIP Evaluation Suite (IN-1K, Caltech, CUB, DTD, ESAT, FLO, SUN, UCF) on the test split.

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) | Standard CLIP Evaluation Suite (IN-1K, Caltech, CUB, DTD, ESAT, FLO, SUN, UCF) (test) |
| Metric | IN-1K 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

- [IN-1K Accuracy](<https://www.sota2.com/research/sota/image-classification-on-standard-clip-evaluation-suite-in-1k-caltech-cub-dtd-esat-flo-sun-ucf-test.md?metric=IN-1K%20Accuracy>): Higher is better; unit: PERCENT.

- [Caltech Accuracy](<https://www.sota2.com/research/sota/image-classification-on-standard-clip-evaluation-suite-in-1k-caltech-cub-dtd-esat-flo-sun-ucf-test.md?metric=Caltech%20Accuracy>): Higher is better; unit: PERCENT.

- [CUB Accuracy](<https://www.sota2.com/research/sota/image-classification-on-standard-clip-evaluation-suite-in-1k-caltech-cub-dtd-esat-flo-sun-ucf-test.md?metric=CUB%20Accuracy>): Higher is better; unit: PERCENT.

- [DTD Accuracy](<https://www.sota2.com/research/sota/image-classification-on-standard-clip-evaluation-suite-in-1k-caltech-cub-dtd-esat-flo-sun-ucf-test.md?metric=DTD%20Accuracy>): Higher is better; unit: PERCENT.

- [ESAT Accuracy](<https://www.sota2.com/research/sota/image-classification-on-standard-clip-evaluation-suite-in-1k-caltech-cub-dtd-esat-flo-sun-ucf-test.md?metric=ESAT%20Accuracy>): Higher is better; unit: PERCENT.

- [FLO Accuracy](<https://www.sota2.com/research/sota/image-classification-on-standard-clip-evaluation-suite-in-1k-caltech-cub-dtd-esat-flo-sun-ucf-test.md?metric=FLO%20Accuracy>): Higher is better; unit: PERCENT.

- [SUN Accuracy](<https://www.sota2.com/research/sota/image-classification-on-standard-clip-evaluation-suite-in-1k-caltech-cub-dtd-esat-flo-sun-ucf-test.md?metric=SUN%20Accuracy>): Higher is better; unit: PERCENT.

- [UCF Accuracy](<https://www.sota2.com/research/sota/image-classification-on-standard-clip-evaluation-suite-in-1k-caltech-cub-dtd-esat-flo-sun-ucf-test.md?metric=UCF%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy (8 Datasets)](<https://www.sota2.com/research/sota/image-classification-on-standard-clip-evaluation-suite-in-1k-caltech-cub-dtd-esat-flo-sun-ucf-test.md?metric=Average%20Accuracy%20(8%20Datasets)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | IN-1K Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ProAPO | 64.7 | Not recorded | 68fa77641e209131cea7303f |
| iCM | 64.5 | Not recorded | 68fa77641e209131cea7303f |
| Vanilla CLIP | 62.1 | Not recorded | 68fa77641e209131cea7303f |

### ProAPO

IN-1K Accuracy: 64.7. Result ID: 69949cf63a6c3148491e6743.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea7303f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77641e209131cea7303f.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/32","Optimization Protocol":"Automatic Prompt Optimization (w/ 1-shot)"}. This record does not assert independent reproduction.

### iCM

IN-1K Accuracy: 64.5. Result ID: 69949cf63a6c3148491e6742.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea7303f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72381e209131cea550b9.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/32","Optimization Protocol":"Automatic Prompt Optimization (w/ validation set)"}. This record does not assert independent reproduction.

### Vanilla CLIP

IN-1K Accuracy: 62.1. Result ID: 69949cf63a6c3148491e6741.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea7303f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Backbone":"ViT-B/32","Optimization Protocol":"Zero-shot"}. This record does not assert independent reproduction.

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