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
Related terms
Chain-of-Thought
Prompting a model to reason step by step, which tends to improve its accuracy on hard problems.
Inference
Actually running a trained model to get an answer, as opposed to training it in the first place.
Compute
The raw processing power used to train or run a model, a key driver of cost and capability.
Large Language Model
A model trained on massive amounts of text that predicts and generates language, powering tools like ChatGPT and Claude.