Verify evals on Papers with Code

Hi,

Niels here from the open-source team at Hugging Face. Congratulations on your work!

I've made the [paper](https://paperswithcode.co/paper/2309.16671) and [21 paper-native evaluations](https://paperswithcode.co/paper/2309.16671#results) available on Papers with Code.

The paper has results on [Image Classification](https://paperswithcode.co/tasks/image-classification), [Depth estimation](https://paperswithcode.co/tasks/depth-estimation), and [Image Understanding](https://paperswithcode.co/tasks/image-understanding) task pages.

The MetaCLIP ViT-B/32 (2.5B data) result currently ranks second on [ImageNet-O](https://paperswithcode.co/benchmark/imagenet-o?task=image-classification&eval=7256).

The MetaCLIP ViT-L/14 (400M data) result currently ranks second on [CLEVR Distance](https://paperswithcode.co/benchmark/clevr-distance?task=depth-estimation&eval=7242).

The MetaCLIP ViT-bigG/14 result currently ranks third on [PatchCamelyon](https://paperswithcode.co/benchmark/patchcamelyon?task=image-classification&eval=7252).

The MetaCLIP ViT-L/14 (2.5B data) result currently ranks fourth on [CLEVR Count](https://paperswithcode.co/benchmark/clevr-count?task=image-understanding&eval=7241).

Would it be possible to verify these results and let me know if any score, model name, benchmark protocol, or openness metadata should be corrected?

You can also edit the task, methods, project page, and GitHub URL directly from the paper page using your Hugging Face account.

If you'd like to showcase the results in your repository README, you can copy these live leaderboard badges (or use the “Copy PwC badge” button in the Results section):

[](https://paperswithcode.co/api/v1/papers/2309.16671/leaderboard-badge-link?eval=7242)
[](https://paperswithcode.co/api/v1/papers/2309.16671/leaderboard-badge-link?eval=7256)
[](https://paperswithcode.co/api/v1/papers/2309.16671/leaderboard-badge-link?eval=7252)

Kind regards,

Niels