Gemini 3 Pro is not Nano Banana Pro, and the image generation/model that decodes the generated image tokens may not be as robust.
The thinking step of Nano Banana Pro can refine some lateral steps (i.e. the errors in the homework correction and where they are spatially in the image) but it isn't perfect and can encounter some of the typical pitfalls. It's a lot better than Nano Banana base, though.
I actually did this prompt and found that it worked with a single nudge on a followup prompt. My first shot got me a wine glass that was almost full but not quite. I told it I wanted it full to the top - another drop would overflow. The second shot was perfectly full.
do it the other way - give it images of wine glasses and ask it whether they are full to the brim. I suspect it's going to nail them all (mainly because Qwen-VL already does nail things like that).
Prompt: "wine glass full to the brim"
Image generated: 2/3 full wine glass.
True visual and spatial reasoning denied.