Best reasoning LLM in 2026

Our Reasoning rating across all frontier models, with price as a mild tie-breaker. Weights: Out $/1M tok 10%.

A CompareLLM rating is our own verdict for one job — Coding, Reasoning, Writing and so on — at one reasoning effort. It runs roughly 1000 to 2000, like a chess rating: it places a model against the others on that list rather than scoring it out of 100. It is computed from a disclosed recipe of published evidence, each input carrying its source and date, and every rating says how much of that recipe it could actually use. It is our opinion, not an exam mark and not a crowd vote. This list uses a named Stack Engine mix — the category rating is only one input when the job is “best chatbot,” not when the job is “cheapest coding agent.”

Every cell has a source and an as-of date. We noindex thin pages and we do not fill missing scores. Open the model or pair page and read the snapshot.