We tested every major AI reasoning system. There is no clear winner.
Source
arcprize.org
Author
Mike Knoop
Date
Why it matters
Breaks modern reasoning systems into distinct test-time techniques and compares labs on a common benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition →, helping you judge claims that more test-time computeSpending more computation when the model answers — thinking longer, trying multiple attempts — to buy accuracy without training a bigger model.Full definition → leads to general intelligence.
Terms in this piece · Glossary
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
test-time compute — Spending more computation when the model answers — thinking longer, trying multiple attempts — to buy accuracy without training a bigger model.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
