From the source
Microsoft AI has introduced MAI Code 2 and MAI Code 2 Flash, two coding models built for everyday enterprise coding tasks at a fraction of the cost of competing models.
- MAI Code 2 targets production work such as deep debugging, multi-file implementation, repo-wide reasoning and UI, while MAI Code 2 Flash handles high-volume work like code explanations, targeted edits and routine fixes.
- Averaged over four benchmarks aimed at everyday enterprise coding tasks, MAI Code 2 delivers 98% of GPT 6.1 Sol's performance at 40% of the cost and 96% of Claude Opus 5.5's performance at 5% of the cost, according to
Microsoft.
- In blind frontend app evaluations, reviewers preferred MAI Code 2's results over GPT-6 Sol 67% of the time.
- MAI Code 2 Flash offers comparable performance to GPT-6 Luna and Claude Haiku 5.5 at 65% and 20% of the cost across three coding benchmarks.
- Microsoft says the models are explicitly not yet tuned for harder problems such as fundamental science research and very long horizon agentic work.
- Both models are available in
GitHub Copilot, and Code 2 Flash is in limited-access preview in Microsoft Foundry, with releases planned on Open Router,
Vercel, Hermes, Open Code and Kilo.






