AI Agent Glossary · AI Coding Tools Glossary
Reasoning model (extended thinking)
A model that spends extra inference-time compute generating intermediate reasoning before answering, trading latency and cost for accuracy on hard tasks.
Reasoning models (OpenAI o-series, Claude with extended thinking, Gemini thinking, DeepSeek-R1) improve coding benchmark scores markedly — GPT-5 (high) reaches 88% on Aider's polyglot benchmark at $29 per run, while cheaper settings score lower. The cost varies by an order of magnitude across models for similar scores, which is why leaderboards now report dollars alongside percentages.