LLM Models Part 3 - Which Models Do I Actually Use?

🔥

In Part 2, we looked at the range of model capability. Now let’s make it practical.

After more than 100 hours of testing, I have developed a fairly simple approach. I choose the product, model, and reasoning setting based on the type of work I am doing (not cost - yet).

🧠 Heavy Logic, Planning and Structure, for work such as:

Business proposals
Strategic frameworks
Complex planning
Coding
Difficult analysis
Multi-step problem solving
Assignments where maintaining context is critical
Consistency of theme or storyline

For these applications, I want stronger reasoning, even if it takes longer.

Product: ChatGPT

Model: GPT-5.6 Sol

Setting: High reasoning and for my book editor skill, Pro.

Product: Claude

Model: Claude Opus 5

Setting: High effort, with extended thinking when needed

For these assignments, creativity in the delivery is secondary.

My priorities are logic, structure, context integrity, planning, and getting the framework right.

I rarely go higher, but keep in mind, most of what I do is front office business execution: strategy, project management, process refinement, education and training, and Cowork automation.

I use Fable 5 rarely. I am not primarily using Claude to build sophisticated production applications.

✍️ Writing and Everyday Communication, for:

Blog posts
Creative writing
Emails
Business communication
Social posts
Editing and rewriting

I usually want a capable model that leaves a little more room for creativity and variation.

Product: Claude

Model: Claude Sonnet 5

Setting: Standard/default effort

Product: ChatGPT

Model: GPT-5.5 Instant

Setting: Instant

I still use GPT-5.5 for this type of work while it remains available to me.

The Interesting Exception: Image Creation

Image creation breaks my normal rule. Why?

I need the LLM to understand:

What I am trying to communicate
The audience
Composition and hierarchy
Style and mood
The creative objective

So I need reasoning. But I also want the system to have enough freedom to interpret the brief creatively.

Product: ChatGPT

Model: GPT-5.6 Sol

Setting: Lighter reasoning

I think of this informally as “Sol-Light.”

That is my shorthand, not an official OpenAI model name.

For image creation, I want enough reasoning to understand the creative brief without applying maximum deliberation to every creative decision.

🗺️ My Current Model Map:

Heavy logic, planning, frameworks and coding

ChatGPT + GPT-5.6 Sol + High reasoning
Claude/Cowork + Opus 5 + High effort

Exceptionally demanding work, complex planning

Claude/Cowork + Fable 5 + High effort / extended thinking

Blogs, creative writing, email and social communication

Claude + Sonnet 5 + Standard effort
ChatGPT + GPT-5.5 Instant + Instant, while available

Image creation

ChatGPT + GPT-5.6 Sol + lighter reasoning

💡 The Takeaway:

The point is not to memorize these model names. They will change.
The habit I want you to develop is knowing when to dial capability up and when to dial it back.

18 comments

LLM Models Part 3 - Which Models Do I Actually Use?