# Reasoning model

> Reasoning models, like OpenAI o1 and o3-mini, are new large language models trained with reinforcement learning to perform complex reasoning. Reasoning models think before they answer, producing a long internal chain of thought (test-time compute before responding to the user. Reasoning models excel in complex problem solving, coding, scientific reasoning, and multi-step planning for agentic workflows.[^1]

Reasoning models, like OpenAI o1 and o3-mini, are new [large language models](https://wiki.g15e.com/pages/Large%20language%20model.txt) trained with [reinforcement learning](https://wiki.g15e.com/pages/Reinforcement%20learning.txt) to perform complex reasoning. Reasoning models think before they answer, producing a long internal chain of thought ([test-time compute](https://wiki.g15e.com/pages/Test-time%20compute.txt) before responding to the user. Reasoning models excel in complex problem solving, coding, scientific reasoning, and multi-step planning for agentic workflows.[^1]

## Footnotes

[^1]: https://platform.openai.com/docs/guides/reasoning