# Reasoning model

**Source:** https://promtable.com/glossary/reasoning-model

> A reasoning model is an LLM trained to produce extensive internal chain-of-thought before its final answer, trading latency for higher accuracy on hard problems.

---
A reasoning model is an LLM trained to produce extensive internal chain-of-thought before its final answer, trading latency for higher accuracy on hard problems.

Reasoning models — OpenAI o1/o3, Claude 3.5/4 with extended thinking, Gemini 2 Thinking, DeepSeek R1, Qwen QwQ — are post-trained to run long internal CoT (often thousands of tokens of "thinking") before emitting the user-facing answer. They dominate benchmarks on math, code, and multi-step reasoning, but are slower (5–30 seconds typical) and more expensive per query. For trivial tasks they are overkill and add latency. Best practice in 2026 is to route: fast non-reasoning model for chat and extraction, reasoning model for planning, hard math, complex code, and agent step-decisions.

## When to use

- Math, code, complex planning, multi-hop QA.
- Agent step-decisions where one wrong step cascades.
- Anything where 10 extra seconds is worth a 20-point accuracy gain.

## When not to use

- Real-time chat with strict <2 s latency budget.
- Trivial extraction or classification (waste of money).

## Common mistakes

- Adding explicit CoT to a reasoning model — often hurts.
- Using a reasoning model for every API call instead of routing.

## Related terms

- [chain-of-thought](https://promtable.com/glossary/chain-of-thought)
- [agent](https://promtable.com/glossary/agent)
- [system-prompt](https://promtable.com/glossary/system-prompt)

*Last updated: 2026-06-01*
---

Original page: https://promtable.com/glossary/reasoning-model
Maintained by Promtable (https://promtable.com). Content: CC BY 4.0. Cite as "Promtable — https://promtable.com/glossary/reasoning-model".
Contact: info@vibecodingturkey.com.