Getting a text based model to design voxel art really doesn't seem to be a good benchmark...

And the order of the top players is very different...

All the frontier LLMs are multi-modal.

	▲	londons_explore 2 hours ago \| parent [-]
		But voxel-art isn't one of their modes. For other modes like image generation, the model has a dedicated image head, and is jointly trained.