# Image Classification on Multilingual ImageNet-1K 1.0 (test)

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

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

Data updated: 2026-02-26T05:34:30.188Z

Evaluation of Image Classification performance on the test split of the Multilingual ImageNet-1K dataset (Version 1.0), reporting accuracy metrics across specific languages (EN, ZH, JP, AR, IT) and their average.

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) | Multilingual ImageNet-1K 1.0 (test) |
| Metric | Accuracy (ZH) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

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

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

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

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

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

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

## Recorded results

| Method | Accuracy (ZH) | Result date | Report paper |
| --- | --- | --- | --- |
| InternVL-C | 64.5 | Not recorded | 68fa71de1e209131cea5370d |
| CN-CLIP-ViT-H | 59.6 | Not recorded | 68fa71de1e209131cea5370d |
| AltCLIP-ViT-L | 59.6 | Not recorded | 68fa71de1e209131cea5370d |
| WuKong-ViT-L-G | 57.5 | Not recorded | 68fa71de1e209131cea5370d |
| OpenCLIP-XLM-R-H | 55.7 | Not recorded | 68fa71de1e209131cea5370d |
| Taiyi-CLIP-ViT-H | 54.4 | Not recorded | 68fa71de1e209131cea5370d |
| OpenCLIP-XLM-R-B | 42.7 | Not recorded | 68fa71de1e209131cea5370d |
| EVA-02-CLIP-E+ | 3.6 | Not recorded | 68fa71de1e209131cea5370d |

### InternVL-C

Accuracy (ZH): 64.5. Result ID: 6991eabc3a6c3148490b6a1d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Implementation](<https://github.com/OpenGVLab/InternVL>)

Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction.

### CN-CLIP-ViT-H

Accuracy (ZH): 59.6. Result ID: 6991eabc3a6c3148490b6a18.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f661e209131cea4556a.md>)

[Implementation](<https://github.com/OFA-Sys/Chinese-CLIP>)

Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction.

### AltCLIP-ViT-L

Accuracy (ZH): 59.6. Result ID: 6991eabc3a6c3148490b6a19.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d07c.md>)

[Implementation](<https://github.com/FlagAI-Open/FlagAI>)

Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction.

### WuKong-ViT-L-G

Accuracy (ZH): 57.5. Result ID: 6991eabc3a6c3148490b6a17.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d821e209131cea3a343.md>)

[Implementation](<https://wukong-dataset.github.io/wukong-dataset/>)

Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction.

### OpenCLIP-XLM-R-H

Accuracy (ZH): 55.7. Result ID: 6991eabc3a6c3148490b6a1c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction.

### Taiyi-CLIP-ViT-H

Accuracy (ZH): 54.4. Result ID: 6991eabc3a6c3148490b6a16.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee41e209131cea42ac7.md>)

Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction.

### OpenCLIP-XLM-R-B

Accuracy (ZH): 42.7. Result ID: 6991eabc3a6c3148490b6a1b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction.

### EVA-02-CLIP-E+

Accuracy (ZH): 3.6. Result ID: 6991eabc3a6c3148490b6a1a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71de1e209131cea5370d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ede1e209131cea42844.md>)

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

Recorded evaluation configuration: {"zero-shot":true}. This record does not assert independent reproduction.

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