Prompting & Inference

Reasoning Model

A model trained to think step by step before answering, spending extra compute at inference time to solve harder problems.

A reasoning model generates a long internal chain of thought before giving its final answer, effectively working through the problem on scratch paper first. This trades speed and tokens for accuracy, and it shines on math, coding, and multi-step logic where a quick answer often fails. The approach, seen in models like the OpenAI o-series and DeepSeek R1, popularized the idea of test-time compute: letting a model think longer to get smarter.

Reference: Wikipedia: Reasoning Model