# Reasoning Devrim: OpenAI o1'den DeepSeek-R1'e — Test-Time Compute ve Chain-of-Thought'un Yeniden Doğuşu

> Source: https://sukruyusufkaya.com/learn/llm-muhendisligi/reasoning-models-o1-deepseek-r1-test-time-compute
> Updated: 2026-08-23T00:07:39.121Z
> Category: LLM Mühendisliği
> Module: Modül 17: Reasoning Models — o1, DeepSeek-R1, Test-Time Compute
**TLDR:** 2024-2026 LLM frontier'ı: reasoning models. OpenAI o1 (Eylül 2024), DeepSeek-R1 (Ocak 2025) devrim. Test-time compute scaling (Kaplan'ın yeni boyutu), chain-of-thought intensification, hidden reasoning tokens (o1) vs visible (R1), RL training reasoning patterns. AIME, MATH benchmark devrim, GPT-4 → o1 90% accuracy sıçraması.