Controlling Reasoning Effort in LLMs
Sebastian Raschka discusses the evolution of reasoning-based LLMs, specifically focusing on the new GPT-5.6 model family. He explains how developers can implement multiple reasoning-effort modes to optimize model performance.
Why it matters
Understanding how to control reasoning effort is critical for optimizing LLM performance and cost-efficiency in enterprise applications.
Sebastian Raschka, PhD Jul 18, 2026 243 11 19 Share It has been almost two years since OpenAI released o1, a model that popularized the idea of LLM-based reasoning models. DeepSeek-R1 followed about four months later, together with details of a reinforcement learning with verifiable rewards (RLVR) recipe to train such reasoning models.
Last week, OpenAI released the GPT-5.6 model family. It comes in three sizes, each with roughly five or six reasoning-effort settings.
Figure 1: The GPT 5.6 Sol model with different reasoning effort settings. (Benchmark numbers for Ultra are currently not available but should be relatively similar to Max, since it uses a similar effort level but accelerates the work with four subagents.)
So yes, reasoning models are here to stay. They have become a standard part of modern model releases.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in