The Copilot Model Picker Nobody Switches: When to Use Default, GPT-5.5 or Claude Opus

Open Microsoft 365 Copilot Chat and look near the prompt box. There is a small control that lets you choose which model answers you. Most people never touch it.

That is not a criticism. The picker is easy to miss and Copilot works fine if you leave it alone. But leaving it alone has a cost. Every prompt you send, the routine ones and the hard ones, goes to the same default model. You are paying for capability you never switch on.

This is a guide to the picker. What the three options are, when to reach for each and why you never have to leave Microsoft to do it.

The three options, in plain English

The picker in Copilot Chat usually gives you three choices.

Start with Microsoft’s default. It is the model Copilot uses unless you tell it otherwise. It is quick, capable and well suited to the bulk of daily work: drafting an email, summarising a thread, tidying up notes, pulling the key points from a document. For most prompts, most days, it is the right tool and you will not need to change a thing.

Next is the OpenAI option. When this guide was written that meant GPT-5.5, and the picker is now gaining GPT-5.6, which began rolling out across Copilot in July. Reach for it when a task needs sustained reasoning rather than a quick turnaround: working through a multi-step analysis, structuring a messy problem, drafting something where the logic has to hold together from start to finish.

Then there is Claude Opus, Anthropic’s model. This began as Claude Opus 4.8, which arrived in Copilot on launch day, and the picker now carries Claude Opus 5. Its strength is careful reading and a habit of flagging when it is not sure rather than bluffing, which matters when you are reviewing a document closely or working on anything high stakes.

If you want the background on why Copilot offers more than one model at all, our plain-English guide to the models behind Copilot covers it, and our look at how Copilot, ChatGPT and Claude compare for business work sits alongside this. This piece is narrower. It is about which one to pick, for which job, inside Copilot.

What it costs to leave it on default

Here is the quiet problem. If nobody in the firm ever switches the model, the default handles everything. The forecast with linked assumptions, the contract you are reading line by line, the board paper that has to be right: all of it runs on the model tuned for speed and routine work.

The default is good. It is not always the best tool for the heaviest jobs. When you never switch, you leave the more capable models sitting in the menu, unused, on exactly the work that would benefit from them. You have already paid for them in the licence. The skill is knowing when to reach for them.

There is no penalty for the default doing routine work. That is what it is for. The cost is invisible, which is what makes it easy to ignore: a slightly weaker answer on a hard question, accepted because nobody knew there was a better option one click away.

The hardest questions tend to land at month-end and in the run-up to a deadline, when the least time arrives with them. Those are exactly the moments the default is asked to do work it was not built for, because switching does not occur to anyone under pressure. Knowing the heavier models are there, and reaching for them by reflex, is what turns the picker from a buried setting into a useful tool.

A simple rule, by the job in front of you

You do not need a decision tree. A rough sort by the kind of work in front of you covers most cases.

• Routine drafting and summaries. Emails, meeting notes, first-draft documents, quick summaries. Leave it on the default. Switching here buys you little and slows you down.
• Heavier analysis and reasoning. Multi-driver forecasts, structured analysis, problems with several moving parts. Switch to GPT-5.5 or Claude Opus and give the model room to work.
• Careful or high-stakes review. Close document review, anything client-facing, anything with a number or a clause that has to be right. Switch, then check the output yourself. A more capable model raises the quality of the draft. It does not remove your responsibility for the result.

That last point is the one people skip. Switching to a stronger model is not a substitute for review. It gives you a better starting draft for the review you were always going to do.

Where else the model choice shows up

The picker in Copilot Chat is the obvious place, but it is not the only one.

Claude Opus is not limited to chat. It also turns up in agent mode, the Edit with experience inside Word, Excel and PowerPoint. It is in Copilot Cowork as well, for anyone with a Microsoft 365 Copilot licence. So the model choice is not just a chat setting. It reaches into the documents and workbooks where the real work happens, which is usually where the harder reasoning is needed anyway.

The same instinct applies wherever the choice appears. A routine edit to a slide or a quick formula does not need a heavier model. Restructuring a financial model, reworking a complex clause or drafting a careful analysis might. You are making the same judgement you make in chat, just closer to the document. It is worth telling people the choice exists in these places too, because most assume the model is fixed once they leave the chat pane.

A second dial: response modes

Model choice is one lever. Copilot has another that is easy to confuse with it.

Separate from which model answers, you can choose how it responds: Auto, Quick Response or Think Deeper. Quick Response is faster and lighter. Think Deeper spends longer on harder questions. Auto decides for you. It is worth knowing the setting exists, but it is a different dial from the model picker and not one to overthink. Pick the model for the job first.

The governance point, and a sense of proportion

One caution, and it matters most in regulated work. Using Anthropic’s Claude models inside Copilot is not automatic. Your organisation has to approve Anthropic models first. Anthropic operates as a Microsoft subprocessor, so Microsoft’s data protection terms still apply, but the processing sits outside the Microsoft EU Data Boundary, and in the UK the models are off by default in the admin centre for that reason. We cover the decision in full in our look at Claude Opus 5 in Copilot.

That is worth a deliberate decision, not a quiet switch-on. The right people should sign it off, with an eye on where the work goes. But keep it in proportion. Running the work through Claude inside Copilot is far safer for client data than the habit it usually replaces, which is someone pasting the same content into public ChatGPT or Claude.ai on a personal account. Inside Copilot the work stays in the governed tenant, under your controls. The fuller picture is in our practical guide to using Copilot with client data.

Make switching a habit, not a one-off

The picker only helps if people use it, and they will not if it stays a piece of trivia from a training session. The fix is not a long policy. It is a few clear defaults the team can remember.

A simple version works well. Routine work stays on the default, so nobody has to think about it. Named jobs always get a switch: the monthly forecast, contract review, the board pack, the client letter. When someone is about to send work that carries a number or a commitment, that is the prompt to check which model produced it. Written down in a line or two, that is enough to change behaviour. The aim is not to switch constantly. It is to switch on purpose, on the work that warrants it.

Knowing when to switch is the skill

Microsoft’s own line is that having more than one model is a deliberate advantage, not a workaround, and on this they are right. The choice is the point. The default covers the routine. The heavier models are there for the work that earns them. And all of it sits inside Microsoft 365, governed through your tenant, so you do not have to send client data to an outside tool to get a more capable answer.

Knowing when to switch is the skill, and it does not come from a licence. It comes from showing people the work, not the feature. If you want this applied to a specific kind of job, we have gone deeper on two: which Copilot model your finance team should use for forecasting and variance work, and choosing a Copilot model for legal document review for law firms weighing the governance.

Where a job repeats often enough that nobody should be choosing a model by hand, a Copilot Studio agent earns its place, and building those agents is the work we do. If you want to talk it through, book a free consultation and we will start from the work in front of you.