MAI-Thinking-1 | Microsoft AI
Built for the complex problems that matter most, with competitive reasoning and top SWE-Bench Pro results at a mid-weight price. Helps your engineering team write better code faster, with a lightweight, agentic model built into GitHub Copilot and VS Code. Create stunning, design-ready images from any text or photo prompt, with best-in-class Arena ELO scores at a lower price. Turn noisy audio into precise, domain-specific transcripts, with leading FLEURS and Artificial Analysis accuracy scores. The latest breakthroughs and updates from within our team MAI-Thinking-1 (35B active, ~1T total parameters, MoE) has a smaller inference footprint than much larger models, yet is competitive with Claude Opus 4.6 on SWE-Bench Pro—coding power that you can run every day. MAI-Thinking-1 (35B active, ~1T total parameters, MoE) has a smaller inference footprint than much larger models, yet is competitive with Claude Opus 4.6 on SWE-Bench Pro—coding power that you can run every day. Independent human r
Explore this link on the map →