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/2601.10611) and [20 verified paper-native evaluations](https://paperswithcode.co/paper/2601.10611#results) available on Papers with Code.

The paper has results on [Image Understanding](https://paperswithcode.co/tasks/image-understanding), [Video Understanding](https://paperswithcode.co/tasks/video-understanding), [Document Understanding](https://paperswithcode.co/tasks/document-understanding), and 1 additional task page.

The Molmo2-8B result currently ranks first on [VQAv2](https://paperswithcode.co/benchmark/vqav2?task=image-understanding&eval=9525).

The Molmo2-4B results currently rank second on [LongVideoBench](https://paperswithcode.co/benchmark/longvideobench?task=video-understanding&eval=9517) and [TOMATO](https://paperswithcode.co/benchmark/tomato?task=video-understanding&eval=9514).

The Molmo2-8B result currently ranks second on [AI2D](https://paperswithcode.co/benchmark/ai2d?task=image-understanding&eval=9521).

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/benchmark/vqav2?task=image-understanding&eval=9525)
[](https://paperswithcode.co/benchmark/ai2d?task=image-understanding&eval=9521)
[](https://paperswithcode.co/benchmark/longvideobench?task=video-understanding&eval=9517)
[](https://paperswithcode.co/benchmark/tomato?task=video-understanding&eval=9514)
[](https://paperswithcode.co/benchmark/perception-test?task=video-understanding&eval=9512)
[](https://paperswithcode.co/benchmark/textvqa?task=image-understanding&eval=9524)

Kind regards,

Niels

Start with the Papers with Code page for paper 2601.10611 and review the 20 linked evaluations against the paper and its official release artifacts. Verify each score, model name, benchmark protocol, and openness metadata; done means corrections are identified or the imported rows are confirmed accurate.

由索引模型根據 Issue 內容生成。