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 3 paper-native evaluations available on Papers with Code.

The paper has results on Coding Agents and Agents task pages.

The AutoSaddler result currently ranks first on GAIA2.

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 page and its three paper-native evaluation results, then compare them with the paper or official release artifacts. Verify the score, model name, benchmark protocol, and openness metadata for the AutoSaddler rows, and report any corrections; completion means the imported results are confirmed or the needed changes are identified.