SYSTEM Cited by 1 source
o1-preview¶
Definition¶
o1-preview is OpenAI's first-generation "reasoning" model family, released 2024-09-12. Trained to perform internal chain-of-thought before producing a final answer; positioned for tasks requiring logical reasoning / multi-step problem solving. Preview tier of the o1 line; sibling to o1-mini.
Wiki anchor¶
The wiki's canonical anchor for o1-preview is Yelp's selective use of it for "newer and more complex tasks that require logical reasoning" (2025-02-04 post — sources/2025-02-04-yelp-search-query-understanding-with-llms): "For newer and more complex tasks that require logical reasoning, we have begun using o1-mini and o1-preview in some use cases, depending on the difficulty of the task."
Stub¶
This page is a minimal canonical anchor. Deeper coverage (chain-of-thought mechanics, deliberate-thinking-token trade- offs, o1 → o3 progression) is not walked here.
Seen in¶
- sources/2025-02-04-yelp-search-query-understanding-with-llms — reserved for tasks requiring logical reasoning.
Related¶
- systems/gpt-4 — formulation-phase sibling
- systems/o1-mini — smaller sibling