Core Concepts
Reasoning Model
Also known as: reasoning models, thinking model
In one line
A newer class of LLM that thinks internally before answering, trading speed for accuracy on hard problems.
What does Reasoning Model mean?
Reasoning models (OpenAI o3, DeepSeek R1, Claude with extended thinking) spend compute at inference time on hidden reasoning tokens. They excel at maths, code, and multi-step planning.
A real-world example
Using o3 to work through a complex tax scenario instead of GPT-4o.
Related terms
Large Language Model (LLM)
A neural network trained on huge text collections to predict the next word — the engine behind ChatGPT, Claude and Gemini.
Chain-of-Thought (CoT)
Asking the AI to reason step-by-step before giving its final answer.
Inference
The act of running a trained model to get an answer — as opposed to training it.