Glossary · Phase 2 · Math, when you need it
Paired comparison
Testing two options on the same items and looking at where they disagree. Shared items cancel out differences in difficulty.
Try it now
If the two models were equally good, each disagreement would be a coin flip. z measures how lopsided the flips came out, in units of the usual wobble.
Learn it properly
Comparing two models on the same test · Paired results, disagreements, a quick z and a bootstrap for the gap between two models. About 25 minutes.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.