The last 3.2 points of rewrite edit quality cost 5.6×.

On Potion's measured rewrite-edit suite, one model scored 0.933 at $0.2974 per thousand requests while another scored 0.901 at $0.0536. Both figures come from the same held-out rewrite edit suite, 100 scored items, measured the same way — so the comparison is like for like.

The premium buys 3.2 quality points on this suite. Whether that is worth 5.6× the price depends on what a failure costs you: at high volume with a cheap retry, it usually is not; on work that ships unreviewed, it can be.

Someone is paying the difference. If that is you, the question worth asking is which of these two numbers your workload actually needs — and this is the measurement that answers it.

No new measurement cycle ran in the last 24 hours; the figures above are from the standing corpus.

The current numbers live on the measured answers; the method is public.