# Image Classification on ImageNet-100 1.0 (test)

Source: [Image Classification on ImageNet-100 1.0 (test)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-1-0-test>)

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

Data updated: 2026-02-26T05:38:30.091Z

Evaluation of Image Classification performance on the test split of ImageNet-100 version 1.0, measured using feature similarity metrics derived from models like CLIP, DINO-v2, and EVA-02.

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-100 1.0 (test) |
| Metric | CLIP Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [CLIP Score](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-1-0-test.md?metric=CLIP%20Score>): Higher is better; unit: PERCENT.

- [DINO-v2 Score](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-1-0-test.md?metric=DINO-v2%20Score>): Higher is better; unit: PERCENT.

- [EVA-02 Score](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-1-0-test.md?metric=EVA-02%20Score>): Higher is better; unit: PERCENT.

- [MoCo-v3 Score](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-1-0-test.md?metric=MoCo-v3%20Score>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-1-0-test.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | CLIP Score | Result date | Report paper |
| --- | --- | --- | --- |
| Full Dataset | 92.5 | Not recorded | 69857586c97a0b3e3b5d5c3c |
| Ours (SFM+CI) | 92.2 | Not recorded | 69857586c97a0b3e3b5d5c3c |
| Ours (SFM) | 86.7 | Not recorded | 69857586c97a0b3e3b5d5c3c |
| LGM | 84.9 | Not recorded | 69857586c97a0b3e3b5d5c3c |
| Centroids | 77.1 | Not recorded | 69857586c97a0b3e3b5d5c3c |
| Neighbors (SFM) | 72.2 | Not recorded | 69857586c97a0b3e3b5d5c3c |
| Neighbors (LGM) | 67.8 | Not recorded | 69857586c97a0b3e3b5d5c3c |
| Random | 56.6 | Not recorded | 69857586c97a0b3e3b5d5c3c |

### Full Dataset

CLIP Score: 92.5. Result ID: 69973e865698665ec48f1dee.

[Reporting paper](<https://www.sota2.com/research/paper/69857586c97a0b3e3b5d5c3c.md>)

Recorded evaluation configuration: {"Train Set":"Full"}. This record does not assert independent reproduction.

### Ours (SFM+CI)

CLIP Score: 92.2. Result ID: 69973e865698665ec48f1ded.

[Reporting paper](<https://www.sota2.com/research/paper/69857586c97a0b3e3b5d5c3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69857586c97a0b3e3b5d5c3c.md>)

Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction.

### Ours (SFM)

CLIP Score: 86.7. Result ID: 69973e865698665ec48f1dec.

[Reporting paper](<https://www.sota2.com/research/paper/69857586c97a0b3e3b5d5c3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69857586c97a0b3e3b5d5c3c.md>)

Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction.

### LGM

CLIP Score: 84.9. Result ID: 69973e865698665ec48f1deb.

[Reporting paper](<https://www.sota2.com/research/paper/69857586c97a0b3e3b5d5c3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/691ff210d6b0dd334292e6dd.md>)

Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction.

### Centroids

CLIP Score: 77.1. Result ID: 69973e865698665ec48f1de8.

[Reporting paper](<https://www.sota2.com/research/paper/69857586c97a0b3e3b5d5c3c.md>)

Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction.

### Neighbors (SFM)

CLIP Score: 72.2. Result ID: 69973e865698665ec48f1dea.

[Reporting paper](<https://www.sota2.com/research/paper/69857586c97a0b3e3b5d5c3c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69857586c97a0b3e3b5d5c3c.md>)

Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction.

### Neighbors (LGM)

CLIP Score: 67.8. Result ID: 69973e865698665ec48f1de9.

[Reporting paper](<https://www.sota2.com/research/paper/69857586c97a0b3e3b5d5c3c.md>)

Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction.

### Random

CLIP Score: 56.6. Result ID: 69973e865698665ec48f1de7.

[Reporting paper](<https://www.sota2.com/research/paper/69857586c97a0b3e3b5d5c3c.md>)

Recorded evaluation configuration: {"Train Set":"1 Img/Cls"}. This record does not assert independent reproduction.

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