Compare AI models
Choose anywhere from two to five models and every benchmark score and listed price we have sourced for them lines up in one table.
Narrow it down to exactly two and the table adds a Signal column — the same real-gap-or-noise call this site runs on every head-to-head.
Start from a written verdict
One click — the pair loads with its editorial call on top.
Pick at least two models to see a scored table, or jump straight to one of the editorial verdicts below.
How to read a comparison
The Signal column is a pairwise call, not a ranking — it only ever judges the two models you picked against each other, on one benchmark at a time. A real gap on one benchmark says nothing about another; a model can lead on coding and trail on reasoning in the same comparison. Unverified means at least one of the two scores is still vendor-only — treat the gap as a claim, not a confirmed result, until an independent run backs it up. The full rules behind every label are on methodology.