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/2207.04672) and [2 paper-native evaluations](https://paperswithcode.co/paper/2207.04672#results) available on Papers with Code.

The paper is part of the [Machine Translation](https://paperswithcode.co/tasks/machine-translation) task page.

The NLLB-200 (54.5B MoE) result currently ranks second on [FLORES-101](https://paperswithcode.co/benchmark/flores-101?task=machine-translation&eval=839).

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/2207.04672/leaderboard-badge-link?eval=840)
[](https://paperswithcode.co/api/v1/papers/2207.04672/leaderboard-badge-link?eval=839)

Kind regards,

Niels

Open the linked Papers with Code paper, FLORES-101 benchmark, and result pages; compare the listed scores, model name, protocol, and openness metadata with the paper. Done means confirming the entries or reporting any corrections to Niels.

Written by the indexing model from the issue text.