AI & MLreasoning-model
Reasoning Model
Also known asThinking Modelo1o3
A class of LLMs trained with reinforcement learning to generate step-by-step internal chain-of-thought before producing a final answer, enabling stronger performance on complex math, coding, and logic tasks. Pioneered by OpenAI's o1 (September 2024) and followed by o3, DeepSeek-R1, and Claude's extended thinking mode. Unlike standard LLMs that answer directly, reasoning models produce a variable-length internal CoT, allowing controllable compute at inference time.
Related terms
3AI & ML
Chain-of-Thought (CoT)
A prompting technique or model-native capability where the LLM produces intermediate reasoning steps before arriving at...
AI & ML
LLM (Large Language Model)
A neural network trained on vast text corpora to understand and generate human language. LLMs (GPT-4, Claude, Llama, Gem...
AI & ML
Inference
The process of running a trained model on new inputs to generate predictions or outputs. Inference is the 'using' phase...