EP 52 5 min with Stella & Liam

Microsoft MAI Code 2: Near-Frontier Coding at 5% of the Cost?

Microsoft launched MAI Code 2 and MAI Code 2 Flash at Ignite on November 17, 2026, and both are generally available now in GitHub Copilot. Microsoft claims near-frontier coding performance at a fraction of the cost, with a 50% promotional price in the fine print.

AI Stella and Liam are AI hosts with AI-generated voices. About our AI hosts

Key takeaways

  1. Microsoft launched MAI Code 2 and MAI Code 2 Flash at Ignite on November 17, 2026. Code 2 is built for everyday engineering like debugging and multi file changes; Flash is aimed at high volume jobs like explanations, targeted edits, and routine fixes.
  2. Microsoft claims Code 2 reaches 98% of GPT-6.1 Sol performance at 40% of the cost, and 96% of Claude Opus 5.5 performance at 5% of the cost, averaged over selected coding evaluations at maximum reasoning effort.
  3. The fine print matters: three tests ran on Microsoft's internal platform through the GitHub Copilot CLI without subagents, the figures are vendor reported and not independently reproduced, and the MAI cost math uses a 50% promotional price.
  4. Trying it takes one click: both models are generally available in the GitHub Copilot model picker, and Code 2 Flash is also in limited preview in Microsoft Foundry.
  5. Microsoft says the models are not yet tuned for harder problems, including fundamental science and very long running agent work, so keep a frontier model for the hardest jobs.

Show notes

Microsoft launched MAI Code 2 and MAI Code 2 Flash at Ignite on November 17, 2026, and both are generally available now in GitHub Copilot. Microsoft claims Code 2 reaches 98% of GPT-6.1 Sol performance at 40% of the cost, and 96% of Claude Opus 5.5 performance at 5% of the cost, on selected coding evaluations at maximum reasoning effort. The MAI cost math uses a 50% promotional price, and Microsoft says the models are not yet tuned for harder problems, including very long running agent work. In this episode of Agentic Pod, Liam and Stella explain what shipped, read the fine print, show how to try it in the Copilot model picker, and give an honest verdict.

What we cover:

  • What shipped: MAI Code 2 for everyday engineering work like debugging, multi file changes and user interface work, and Code 2 Flash for high volume jobs like explanations, targeted edits and routine fixes
  • Availability: generally available in GitHub Copilot, with Code 2 Flash also in limited preview in Microsoft Foundry
  • The headline numbers: 98% of GPT-6.1 Sol performance at 40% of the cost, and 96% of Claude Opus 5.5 performance at 5% of the cost, per Microsoft’s own selected evaluations
  • The fine print: selected coding evaluations at maximum reasoning effort, three tests on Microsoft’s internal platform through the GitHub Copilot CLI without subagents, and MAI costs calculated at a 50% promotional price
  • How to try it step by step: open GitHub Copilot, open the model picker, pick Code 2 or Code 2 Flash, and test it on a real task from your own work
  • A real workflow: Flash for the pile of small fixes, Code 2 for debugging across files, and a frontier model saved for the hardest problem
  • Gotchas: not yet tuned for harder problems or very long running agent work, promo pricing, and vendor run benchmarks

Chapters

Questions answered in this episode

What is MAI Code 2?

Microsoft's own coding model, launched at Ignite on November 17, 2026. It is built for everyday engineering work like debugging, multi file changes, and user interface work, and it is generally available in GitHub Copilot.

What is MAI Code 2 Flash?

The smaller, faster model in the same launch, aimed at high volume tasks like explanations, targeted edits, and routine fixes. It is in GitHub Copilot and in limited preview in Microsoft Foundry.

Should I trust the 98% and 96% numbers?

They are Microsoft's own figures, averaged over selected coding evaluations at maximum reasoning effort, with three tests on Microsoft's internal platform, and the cost side uses a 50% promotional price. Treat them as a reason to test the models on your own work, not as a settled result.

How do I try MAI Code 2?

Open GitHub Copilot, open the model picker, pick Code 2 or Code 2 Flash, and give it a real task from your own work. Compare the result and the bill against your usual model.

Links & resources

Full transcript

Intro

Liam

Hey hey hey, welcome to Agentic Pod! I'm Liam.

Stella

And I'm Stella! Liam, Microsoft launched MAI Code 2 at Ignite on November 17th, and the headline is a price claim?

Liam

A big one. Microsoft says Code 2 reaches 98 percent of GPT-6.1 Sol performance at 40 percent of the cost.

Stella

And against Claude?

Liam

96 percent of Claude Opus 5.5 performance at just 5 percent of the cost. By the end you will know what is real, what is fine print, and how to try it today.

What Microsoft actually shipped

Stella

Okay, plain words. What is MAI Code 2?

Liam

It is Microsoft's own coding model. It is made for everyday engineering work, like debugging, changes across files, and user interface work.

Stella

And there is a smaller one too?

Liam

Code 2 Flash. That one is aimed at high volume jobs. Explanations, targeted edits, and routine fixes.

Stella

So one model for the deep work, one for the quick jobs.

Liam

Exactly. And both are generally available now inside GitHub Copilot. Flash is also in a limited preview inside Microsoft Foundry.

Stella

Wait, it is already in Copilot? No waitlist, no new tool to install?

Liam

No new tool. It sits in the model picker, next to the models you already use. Which raises the obvious question, how much should you trust those headline numbers?

The numbers, and the fine print

Stella

Right. 98 percent and 96 percent sound huge. What did Microsoft actually measure?

Liam

Selected coding evaluations, averaged together. The models ran at maximum reasoning effort, and three of the tests ran on Microsoft's own internal platform, through the GitHub Copilot CLI, without subagents.

Stella

So it is Microsoft's test, on Microsoft's setup.

Liam

Yes, and nobody outside Microsoft has reproduced it yet. It does not mean the model finishes 98 percent of your real tasks. It is a relative score on their tests.

Stella

And the cost side? That 5 percent number?

Liam

Here is the catch. The MAI cost math uses a 50 percent promotional price. So the comparison is real on paper, but it is priced at half price.

Stella

Half price, full headline. Classic.

Liam

Classic, but still interesting. A cheaper model that needs three retries can cost more than a pricey model that nails it first try. So what does trying it look like?

How to try it, and a real workflow

Liam

Step one, open GitHub Copilot, in your editor or the Copilot CLI. Step two, open the model picker.

Stella

The same picker where I choose between models today?

Liam

The same one. Pick MAI Code 2 for a bigger job, or Code 2 Flash for a quick one. Step three, give it a real task from your own work, not a toy prompt.

Stella

Like what?

Liam

Like, explain this function and fix the failing test next to it. Then compare. Same task, your usual model, check the result and the bill.

Stella

And Foundry?

Liam

If your team builds on Microsoft Foundry, Flash is there in limited preview. But for most people, Copilot is the front door. Now, where does this actually fit in a normal day?

Liam

Picture a normal morning. You have a bug report, a small feature, and a pile of small fixes waiting.

Stella

The pile is always the worst part.

Liam

Send the pile to Flash. Explain this code, make this targeted edit, fix this routine bug. Fast, cheap, high volume work.

Stella

And the bug report?

Liam

That goes to Code 2. Debugging across files is exactly what Microsoft built it for. It reads the repo, follows the change across files, and works on the fix.

Stella

So you split the day by job size, not by loyalty to one model.

Liam

That is the whole play. Save the expensive frontier model for the one hard problem that truly needs it. Which brings us to the limits, and Microsoft stated them itself...

Gotchas and the honest verdict

Stella

Gotchas. Start with the one Microsoft admitted.

Liam

Microsoft says these models are not yet tuned for harder problems. That includes fundamental science and very long running agent work.

Stella

So no overnight autonomous agent runs on this yet?

Liam

Not the pitch, no. Second gotcha, the promo price. The cheap math depends on a 50 percent promotional price, and nobody should budget a whole year on a launch discount.

Stella

And third, the benchmarks are Microsoft's own.

Liam

Right. Selected tests, max reasoning, internal platform. Promising, but your repo is the only test that counts. Honest verdict, then. Who is this for?

Stella

If you live in GitHub Copilot, try it this week. It costs you one model picker click.

Liam

Agreed. If you run lots of routine coding work, the Flash split could save real money. If you need the hardest long agent runs, keep your frontier model close. The step by step guide is in the description. Would you switch your daily coding model for a cheaper one at 96 percent? Tell us in the comments. See you next time!