# Image Classification on ImageNet-1K (val) (Zero-Shot Top-1 Accuracy)

Source: [Image Classification on ImageNet-1K (val) (Zero-Shot Top-1 Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-zero-shot-top-1-accuracy>)

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

Data updated: 2026-02-26T06:06:54.462Z

Evaluation of Image Classification performance on the validation split of ImageNet-1K using a zero-shot methodology, reporting Top-1 accuracy.

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 (val) |
| Metric | Top-1 Acc (Zero-Shot) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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 Acc (Zero-Shot)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-zero-shot-top-1-accuracy.md?metric=Top-1%20Acc%20(Zero-Shot)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Acc (Zero-Shot) | Result date | Report paper |
| --- | --- | --- | --- |
| CLIP | 76.6 | Not recorded | 68fa72ce1e209131cea58948 |
| SF-LCLIP | 75.9 | Not recorded | 68fa72ce1e209131cea58948 |
| CLIP | 75.4 | Not recorded | 68fa72ce1e209131cea58948 |
| SF-LCLIP | 74.9 | Not recorded | 68fa72ce1e209131cea58948 |
| SF-LCLIP | 73.6 | Not recorded | 68fa72ce1e209131cea58948 |
| CLIP | 68.3 | Not recorded | 68fa72ce1e209131cea58948 |
| SF-BCLIP | 66 | Not recorded | 68fa72ce1e209131cea58948 |
| TinyCLIP | 64.5 | Not recorded | 68fa72ce1e209131cea58948 |
| CLIP | 63.3 | Not recorded | 68fa72ce1e209131cea58948 |

### CLIP

Top-1 Acc (Zero-Shot): 76.6. Result ID: 699297863a6c314849100054.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

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

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

Recorded evaluation configuration: {"visual encoder":"ViT-L/14-336","visual FLOPS":"191.0G"}. This record does not assert independent reproduction.

### SF-LCLIP

Top-1 Acc (Zero-Shot): 75.9. Result ID: 699297863a6c314849100055.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

[Implementation](<https://github.com/showlab/sparseformer>)

Recorded evaluation configuration: {"visual encoder":"SF-LCLIP","tokens":"144","visual FLOPS":"33.9G"}. This record does not assert independent reproduction.

### CLIP

Top-1 Acc (Zero-Shot): 75.4. Result ID: 699297863a6c314849100051.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

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

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

Recorded evaluation configuration: {"visual encoder":"ViT-L/14-224","visual FLOPS":"81.1G"}. This record does not assert independent reproduction.

### SF-LCLIP

Top-1 Acc (Zero-Shot): 74.9. Result ID: 699297863a6c314849100053.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

[Implementation](<https://github.com/showlab/sparseformer>)

Recorded evaluation configuration: {"visual encoder":"SF-LCLIP","tokens":"128","visual FLOPS":"30.0G"}. This record does not assert independent reproduction.

### SF-LCLIP

Top-1 Acc (Zero-Shot): 73.6. Result ID: 699297863a6c314849100052.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

[Implementation](<https://github.com/showlab/sparseformer>)

Recorded evaluation configuration: {"visual encoder":"SF-LCLIP","tokens":"64","visual FLOPS":"14.8G"}. This record does not assert independent reproduction.

### CLIP

Top-1 Acc (Zero-Shot): 68.3. Result ID: 699297863a6c31484910004d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

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

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

Recorded evaluation configuration: {"visual encoder":"ViT-B/16-224","visual FLOPS":"17.5G"}. This record does not assert independent reproduction.

### SF-BCLIP

Top-1 Acc (Zero-Shot): 66. Result ID: 699297863a6c314849100050.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

[Implementation](<https://github.com/showlab/sparseformer>)

Recorded evaluation configuration: {"visual encoder":"SF-BCLIP","tokens":"49","visual FLOPS":"3.8G"}. This record does not assert independent reproduction.

### TinyCLIP

Top-1 Acc (Zero-Shot): 64.5. Result ID: 699297863a6c31484910004f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b01e209131cea4c91a.md>)

Recorded evaluation configuration: {"visual encoder":"ViT-63M/32-224","visual FLOPS":"2.0G"}. This record does not assert independent reproduction.

### CLIP

Top-1 Acc (Zero-Shot): 63.3. Result ID: 699297863a6c31484910004e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea58948.md>)

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

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

Recorded evaluation configuration: {"visual encoder":"ViT-B/32-224","visual FLOPS":"4.4G"}. This record does not assert independent reproduction.

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