Test-time Compute & Reasoning
Concept
Training & Inference
The 2024 discovery: models get smarter by thinking longer.
You're looking at a concept explainer: what this term means in plain English, and the records it ties together.
Reasoning models produce long internal chains of thought before answering, and accuracy scales with how much compute they spend thinking — a new scaling axis alongside model size and data. o1 introduced it; R1 open-sourced it; every frontier model now has a thinking mode. The infrastructure consequence is enormous: a single hard question can cost thousands of times more tokens than a chat reply, shifting demand from training clusters to inference fleets.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Basis for
Related
Sources
Record reviewed as of 2026-01-15 — see Methodology.