GPT 5.6 Configurations and Defaults | Sebastian Raschka, PhD
Skip to main content
🌙
Search this website
Submit search
Yes, there are probably too many options to choose from in the GPT 5.6 release.
In the context of reasoning models, though, I find it interesting how these choices map onto training-time and inference-time scaling. If we loosely map the options onto the classic o1 plots, Sol, Terra, and Luna stand in for three model sizes and training budgets along the training-compute axis. The effort settings then sit on the inference-time-compute axis.
Figure 1. A loose mapping from OpenAI's classic o1 scaling plots to the GPT 5.6 choices. The three model options represent different model sizes and training budgets, while the effort setting represents inference-time compute.
The full list has three model choices and six reasoning-effort levels (Light, Medium, High, Extra High, Max, and Ultra). Once Work versus Codex and Standard versus Fast are included, the full configuration matrix becomes
Work/Codex × Sol/Terra/Luna × Light/Medium/High/Extra High/Max/Ultra × Standard/Fast
That gives us 2 × 3 × 6 × 2 = 72 possible configurations.
So, what is a good default now? Luna with High effort? Sol with Light effort? Terra with Medium effort?
Sure, a performance-versus-cost chart can help identify the good bang-for-the-buck combinations. For instance, Luna with Extra High effort may be better and cheaper than Sol with Medium effort.
Figure 2. Artificial Analysis Coding Agent Index v1.1 scores plotted against API cost across GPT 5.6 and several comparison models. Figure based on OpenAI's GPT 5.6 release post on X.
But yeah, 72 possible configurations leave us with a lot of choices 🤯.
Read Next
Controlling Reasoning Effort in LLMs
Read the longer guide to low-, medium-, and high-effort reasoning modes.
Build a Reasoning Model From Scratch Is Out
Connect model-effort choices to the reasoning-model implementation path.
Reasoning From Scratch
Use the companion hub for chapter links, code, and related reasoning articles.
RSS
Subscribe via Email
tweet or email. -->
© 2013-2026 Sebastian Raschka