I used GPT-5.6 Sol high to optimize it, and it claimed it was getting 50. I'm seeing ~40 on my goto smoketest: "Make me a vector add in CUDA".

Funny side note. It successfully one shot the program, but it wasn't able to run it because there literally wasn't enough VRAM left to allocate CUDA memory. Watching it try to debug that was fascinating. I'm pretty sure it would have killed the llama-server (and thus itself) if it hadn't been running in a separate container.