# Image Classification on ImageNet 1K (Top-1, Top-3, Top-5 Metrics)

Source: [Image Classification on ImageNet 1K (Top-1, Top-3, Top-5 Metrics)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-top-1-top-3-top-5-metrics>)

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

Data updated: 2026-05-08T11:30:15.468Z

Evaluation of Image Classification performance on the ImageNet-1K dataset, reporting Top-1, Top-3, and Top-5 accuracy 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 | Classification |
| Dataset (including any stated split) | ImageNet 1K |
| Metric | Top-1 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-top-1-top-3-top-5-metrics.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

- [Top-3 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-top-1-top-3-top-5-metrics.md?metric=Top-3%20Accuracy>): Higher is better; unit: PERCENT.

- [Top-5 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-top-1-top-3-top-5-metrics.md?metric=Top-5%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DINORANKCLIP | 11.3 | Not recorded | 69fd6e625497b3b670c8979e |
| RANKCLIP | 10.16 | Not recorded | 69fd6e625497b3b670c8979e |
| ALIP | 9.71 | Not recorded | 69fd6e625497b3b670c8979e |
| CyCLIP | 9.4 | Not recorded | 69fd6e625497b3b670c8979e |
| CLIP | 9.06 | Not recorded | 69fd6e625497b3b670c8979e |

### DINORANKCLIP

Top-1 Accuracy: 11.3. Result ID: 69fdc93a47f34ce924e1c0a5.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e625497b3b670c8979e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6e625497b3b670c8979e.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"CC3M","Zero-shot protocol":"true","R":"3"}. This record does not assert independent reproduction.

### RANKCLIP

Top-1 Accuracy: 10.16. Result ID: 69fdc93a47f34ce924e1c0a4.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e625497b3b670c8979e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77971e209131cea7435c.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"CC3M","Zero-shot protocol":"true"}. This record does not assert independent reproduction.

### ALIP

Top-1 Accuracy: 9.71. Result ID: 69fdc93a47f34ce924e1c0a3.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e625497b3b670c8979e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70551e209131cea4a4fc.md>)

[Implementation](<https://github.com/deepglint/ALIP>)

Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"CC3M","Zero-shot protocol":"true"}. This record does not assert independent reproduction.

### CyCLIP

Top-1 Accuracy: 9.4. Result ID: 69fdc93a47f34ce924e1c0a2.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e625497b3b670c8979e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c046.md>)

[Implementation](<https://github.com/goel-shashank/CyCLIP>)

Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"CC3M","Zero-shot protocol":"true"}. This record does not assert independent reproduction.

### CLIP

Top-1 Accuracy: 9.06. Result ID: 69fdc93a47f34ce924e1c0a1.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e625497b3b670c8979e.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","Pre-training Dataset":"CC3M","Zero-shot protocol":"true"}. This record does not assert independent reproduction.

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