Last updated: April 5, 2026 · Prompting & Usage · by Daniel Ashford

What is Chain-of-Thought (CoT)?

QUICK ANSWER

A prompting technique that asks the model to show its reasoning step by step.

Definition

Chain-of-Thought prompting instructs the model to break down its reasoning into explicit, sequential steps before arriving at an answer. This significantly improves accuracy on multi-step reasoning, math, logic, and complex analysis.

How It Works

CoT works because forcing the model to generate intermediate steps gives it more computation — each token builds on previous ones. Modern reasoning models like OpenAI o3 and Claude with extended thinking have CoT built into their architecture.

Example

Without CoT: "What is 17 x 23?" often wrong. With CoT: "Think step by step. 17 x 20 = 340, 17 x 3 = 51, 340 + 51 = 391." — more reliable.

Related Terms

Prompt Engineering
The skill of crafting effective prompts to get the best results from an LLM.
Reasoning Tokens
Hidden thinking tokens that reasoning models generate internally before their visible response.
Prompt
The text input you send to an LLM to get a response.

See How Models Compare

Understanding chain-of-thought (cot) is important when choosing the right AI model. See how 12 models compare on our leaderboard.

View Leaderboard →Our Methodology
← Browse all 47 glossary terms
DA
Daniel Ashford
Founder & Lead Evaluator · 200+ models evaluated