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/2608.13505) and [9 paper-native evaluations](https://paperswithcode.co/paper/2608.13505#results) available on Papers with Code.

The paper has results on [Coding Agents](https://paperswithcode.co/tasks/coding-agents), [Agents](https://paperswithcode.co/tasks/agents), [Image Understanding](https://paperswithcode.co/tasks/image-understanding), and 3 additional task pages.

The Intern-S2-Preview-397B result currently ranks first on [MMLU-Pro](https://paperswithcode.co/benchmark/mmlu-pro?task=language-modeling&eval=26025).

The Intern-S2-Preview-397B result currently ranks third on [HMMT Feb 2026](https://paperswithcode.co/benchmark/hmmt-feb-2026?task=math&eval=26026).

The Intern-S2-Preview-397B result currently ranks fourth on [SWE-Bench Multilingual](https://paperswithcode.co/benchmark/swe-bench-multilingual?task=coding-agents&eval=26031).

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):

[](https://paperswithcode.co/api/v1/papers/2608.13505/leaderboard-badge-link?eval=26025)
[](https://paperswithcode.co/api/v1/papers/2608.13505/leaderboard-badge-link?eval=26026)

Kind regards,

Niels

Review the linked Papers with Code paper, task pages, benchmark results, and the official paper or release artifacts. Compare the score, model name, benchmark protocol, and openness metadata; done means reporting confirmed details or specific corrections to the project team.

Written by the indexing model from the issue text.