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 and 4 verified paper-native evaluations available on Papers with Code.

The paper is part of the Computer Use Agents task page.

The Fara1.5-27B (OSWorld-G Refined) result currently ranks second on OSWorld-G Refined.

The Fara1.5-27B result currently ranks fourth on Online-Mind2Web.

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? The imported rows are tied to the paper or its official release artifacts; comparison-table baselines were not added.

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):

Kind regards,

Niels

Start with the linked Papers with Code paper and its four verified paper-native evaluations, then compare the imported results with the paper and official release artifacts. Check the score, model name, benchmark protocol, and openness metadata for OSWorld-G Refined and Online-Mind2Web; done means confirming them or reporting any corrections.