Encyclopedia · 311 concepts
Learn this concept as a feed

NLP & Language · intermediate · concept 126 of 311 · Updated Nov 4, 2026

Reasoning Models & Test-Time Compute

LLMs trained to produce a long internal chain of reasoning before answering, spending extra compute at inference time to get better answers on math, code, and logic. OpenAI's o-series and DeepSeek-R1 established this as a second scaling axis alongside model size. Most frontier assistants now offer a thinking mode built on this idea.

L7 · LLM and generative AI engineerDevelopersTech leadersProduct leadersQA and testingSEO and content

Top AI contributors on this

Key terms

Test-time computeThinking tokensRLVRVerifiable rewardsLong CoT

Learn these first

Where you meet it in the real world

Competition math, code debugging, scientific analysis, agentic planning

Videos

Guides and articles

Why We Think ↗

Lilian Weng

Courses, papers, and more

This unlocks