Chain of Thought

Chain of thought (CoT) is a prompting technique in which a language model is guided to produce intermediate reasoning steps before its final answer. CoT consistently improves accuracy on multi-step reasoning, arithmetic, and planning tasks by forcing the model to decompose problems rather than pattern-match to a surface answer.

Extended thinking variants (used in Claude's extended thinking mode and OpenAI's o-series) internalize CoT into the model's inference process, enabling deeper reasoning without requiring the prompt to explicitly request step-by-step output.