eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
model routing — Sending each request to a model chosen by the difficulty of the task, rather than using one model for everything.
Why it matters
Concrete numbers for model routingSending each request to a model chosen by the difficulty of the task, rather than using one model for everything.Full definition → in agents — 74% cheaper for roughly six accuracy points — plus the break-even test: judge cost divided by the price gap between the two models is the offload rate you need to clear.
