Add ParseBench-2 evaluation results

#245

This PR ensures your model shows up at https://huggingface.co/datasets/llamaindex/ParseBench-2.

This is based on the evaluation results feature: https://huggingface.co/docs/hub/eval-results.

Includes all six ParseBench-2 dimensions and the overall score.

Thanks for it!!!
Is testing with xhigh planned?

Thanks! Yes, we’ve now run it. The scores here were first from a run with thinking disabled. We reran with thinking on default effort (xhigh) and updated this PR with the xhigh result.
The ParseBench-2 leaderboard now shows these numbers.

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment