Just ask Opus and Kimi to build a game about something random, like "make a Mario Kart-inspired game." Opus gives better results most of the time. That doesn't mean you can't get your particular job done with either of these models.
Yep, one shotting games, UI in general, is where I found them to be lacking, it tracks with my experience.
They do get there with guidance, to me the quality in one shotting things is not relevant though and I don't find I tracking quality on long horizon tasks.