Cool to see another model with support for bounding boxes on images. Really wish to see segmentation in a future release; Gemini 3.5 Flash-Lite is mandatory in my use case as it's the best model for semantic image segmentation in my experience.
I have found a couple of problems Opus could fix that Sol couldn't (smoothing a three way join between curved edges and a bezier curve face is one I can remember). But it's much slower than Sol and generally doesn't produce as nice results.
Assuming I'm not just misunderstanding something critical (happens often!) and you haven't explored this already (very possible!), pointing your agent at this link and asking for some prototypes might be illuminating: https://huggingface.co/models?pipeline_tag=image-segmentatio...