Microsoft Introduces Microsoft-Decision-1, a Decision-Scoring Model for Fast Structured Tasks

Microsoft Launches Microsoft-Decision-1

Microsoft has introduced Microsoft-Decision-1, a new decision-scoring model designed for fast, structured decision-making. The model is available in Microsoft Foundry and through OpenRouter, and it is built for tasks such as routing, classification, prioritization, verification, and workflow control. According to Microsoft, the model delivers top performance in both latency and quality on structured decision tasks, outperforming both large language models and other decision models.

Benchmark Results

In Microsoft's internal testing, Microsoft-Decision-1 achieved the highest accuracy in a 36-benchmark comparison spanning nearly 150,000 questions. The benchmarks were kept blind from training. The company also reported that Microsoft-Decision-1 was the fastest model measured, running 4.5 times quicker than Quyet-1.0-Large, the runner-up, and 35 times quicker than GPT-6 Sol.

A New Category in AI

Microsoft describes decision models as an emerging category in AI that differs from LLMs. While LLMs are designed to generate text or reason through complex problems, decision models are purpose-built to deliver structured outputs that software can immediately act on. The company says this capability, making decisions and classifying things at very low cost with high performance, unlocks a range of useful tasks and makes it easier to incorporate decision intelligence into existing applications, agents, and workflows in a secure, trusted environment.

Sources: commandline.microsoft.com