[andai]

It says Luna is fastest, but doesn't it take way more steps to get the same job done?

https://deepswe.datacurve.ai/ - (See the Agent Steps view)

Or is the output speed so much higher that it cancels out?

I don't see a lot of benchmarks that record actual time. But on AA, Sol on Low beats Luna on High for Time Per Task.

[paxys]

The type of job matters. If it is too complex then yeah, you should be using a larger model.