MAI Code 2 and Code 2 Flash Microsoft released MAI Code 2 and MAI Code 2 Flash, two coding models the company says deliver 98% of GPT-6.1 Sol's performance at 40% of the cost and 96% of Claude Opus 5.5's performance at just 5% of the cost, averaged over four benchmarks (DeepSWE 1.1, Terminal Bench 2.1, SWE-Atlas and FrontierCode v1.1). MAI Code 2 Flash, aimed at high-volume routine coding, matches GPT-6 Luna and Claude Haiku 5.5 at 65% and 20% of their cost across three benchmarks, and in blind frontend app evaluations developers preferred MAI Code 2's results over GPT-6 Sol 64% of the time. Both models are available in GitHub Copilot, with Code 2 Flash in limited-access preview in Microsoft Foundry and planned releases on OpenRouter, Vercel, Hermes, OpenCode and Kilo; Microsoft said the models are not yet tuned for fundamental science research or very long-horizon agentic work. MAI Cyber 2 Flash: Leading security. Lower cost MAI Code 2 and MAI Code 2 Flash: two new coding models built for everyday enterprise coding tasks, delivering leading performance at a fraction of the cost of competing models. MAI Code 2 is at the frontier of price-performance for common enterprise coding tasks and excels in taking code to production, deep debugging, multi-file implementation, repo-wide reasoning, and UI. It does all of this while also delivering changes code maintainers would merge, at a fraction of frontier cost. Meanwhile, MAI Code 2 Flash is designed for high-volume work such as code explanations, targeted edits, routine fixes, and rapid iterations, while bringing quality at a much lower cost. To deliver the best price-performance, we’ve built these models to prioritize the coding work our customers do every day. They’re explicitly not yet tuned for harder problems, like fundamental science research and very long-horizon agentic work. Averaged over four widely used benchmarks that target the everyday enterprise coding tasks we see in GitHub Copilot DeepSWE 1.1, Terminal Bench 2.1, SWE-Atlas and FrontierCode v1.1 , MAI Code 2 gives you 98% of the performance of GPT-6.1 Sol at 40% of the cost, and 96% of Claude Opus 5.5’s performance at just 5% of the cost. 1 fn-1 MAI Code 2 is also tuned for producing great dashboards and visualizations, and excels at visual coding. In blind frontend app evaluations, developers preferred its results over GPT-6 Sol 64% of the time. 2 fn-2 In addition, MAI Code 2 Flash offers comparable performance to GPT-6 Luna and Claude Haiku 5.5 at 6 5% and 20% of the cost, across three coding benchmarks measuring day-to-day, high-volume routine coding tasks. 3 fn-3 MAI Code 2 is also becoming the workhorse behind Microsoft products. From Code 2 Flash, we further optimized a single model, MAI Work Flash, to serve multiple Microsoft products across Microsoft 365 and FabricIQ. Excel: Our model is on par for accuracy and token efficiency with GPT-6 Luna across key internal Excel customer-scenario benchmarks. PowerPoint: On key production benchmark scenarios that measure frequent PowerPoint tasks, our model performs on par with GPT-6 Luna in both quality and token efficiency. Word: Our model performs similarly to GPT-6.1 Sol while being significantly smaller on 5 key internal benchmarks using ~42% fewer input tokens per call than GPT-6.1 Sol in production. Teams: Our model beats GPT-6 Luna at tracking decisions, filling knowledge gaps, and adapting to custom instructions using up to 28% fewer tokens on instruction following and tool calling. FabricIQ: In offline evaluation runs, our MAI model outperforms GPT-5.6 Sol, GPT-6 Astra, and Opus-5.5 at DAX query generation, the core capability behind “Chat with your Data” for Power BI semantic models. Get started MAI Code 2 and Code 2 Flash are available in GitHub Copilot, and Code 2 Flash is in limited-access preview in Microsoft Foundry https://azure.microsoft.com/en-us/products/ai-foundry . Soon, we’ll be releasing them on OpenRouter, Vercel, Hermes, OpenCode, and Kilo. Learn more about customizing MAI Code 2 on our Custom Models page. https://microsoft.ai/models/microsoft-frontier-tuning/ About these results Results reflect evaluations on specific coding tasks and configurations. Performance and cost comparisons vary by workload, model configuration, reasoning effort, and pricing assumptions.