# Pathway says architecture can matter as much as model scale

> A 150M model reached 29. 5% while costing just $0. 0007 per taskChatGPT scored higher, yet its comparable reasoning runs cost substantially moreBDH-CQ performs reasoning internally instead of generating lengthy…

- **Source:** [TechRadar](https://www.techradar.com/pro/11x-cheaper-than-chatgpt-tiny-150m-model-just-proved-ai-doesnt-need-to-think-out-loud-to-be-smart?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=6a7d37a2e06d7577e45dec49)
- **Published:** 2026-08-13
- **Category:** AI & Bots
- **Tags:** #chatgpt #openai #ai
- **Canonical:** http://localhost:4321/a/6a7d37a2e06d7577e45dec49

---

_GearOpen's distilled summary. The full original article is published at TechRadar (source link above); GearOpen does not republish the source's full text._