Article · by Microsoft
Microsoft-Decision-1
Microsoft's decision-scoring model, in Foundry and on OpenRouter.
Satya Nadella
@satyanadella
Introducing Microsoft-Decision-1, our new model for fast decision-making. It delivers top performance on structured decision tasks, outperforming both LLMs and other decision models in latency and quality. We’re already testing it across Microsoft for everything from incident response and quality control to scientific discovery.
Oct 9, 2026 · 11.4K likesOpen on X
Microsoft released Microsoft-Decision-1, a model for fast decision scoring. It is Qwen3.5-9B, post-trained for single-pass scoring, and Microsoft says it will rebase it on other models, including its own and OpenAI's. It supports yes/no, multiple-choice and rating questions, plus rubric-based grading of AI responses and agent actions. Microsoft reports the highest accuracy in its own 36-benchmark comparison, and says it is 35 times quicker than GPT-6 Sol. Microsoft ran these tests itself.
Open the source
