The last 7.3 points of extraction quality cost 38×.

On Potion's measured extraction suite, one model scored 0.977 at $0.5466 per thousand requests while another scored 0.904 at $0.0144. Both figures come from the same held-out extraction suite, 40 scored items, measured the same way — so the comparison is like for like.

The premium buys 7.3 quality points on this suite. Whether that is worth 38× 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.