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/2608.07110) and [8 paper-native evaluations](https://paperswithcode.co/paper/2608.07110#results) available on Papers with Code.

The paper has results on [Language Modeling](https://paperswithcode.co/tasks/language-modeling) and [Reasoning](https://paperswithcode.co/tasks/reasoning) task pages.

You can review, for example, the [ARC-C result](https://paperswithcode.co/benchmark/arc-c?task=language-modeling&eval=29432).

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.

Kind regards,

Niels

Start with the linked Papers with Code paper page, its eight paper-native evaluation rows, and the ARC-C result example. Compare each score, model name, benchmark protocol, and openness metadata with the paper or official release artifacts; done means confirming the entries or reporting the specific corrections needed.

Written by the indexing model from the issue text.