Decision models are quickly emerging as an important new category in AI. Unlike LLMs, which 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. Microsoft-Decision-1, the company's new model for fast decision-scoring, is now available in Microsoft Foundry and coming soon through Open Router.
This model is designed for routing, classification, prioritization, verification, and workflow control, making it easier to incorporate decision intelligence into existing applications, agents, and workflows in a secure, trusted environment. Microsoft-Decision-1 delivers top performance in latency and quality on structured decision tasks to outperform both LLMs and other decision models. It achieved the highest accuracy in a 36-benchmark comparison spanning nearly 150,000 questions, with benchmarks kept blind from training.
In benchmarking, Microsoft-Decision-1 was the fastest measured: 4.5 times quicker than Quyet-1.0-Large, the runner-up, and 35 times quicker than GPT-6 Sol. To build the model, the team post-trained Qwen3.5-9B for fast, single-pass decision scoring. When given a fixed set of answer options, the model provides a calibrated probability score for each option. The model supports yes/no, multiple-choice, and rating options, as well as rubric-based grading of AI responses and agent actions, all through a simple structured API call. Addressing challenges of speed, quality, robustness, probability calibration, and safety, Microsoft-Decision-1 demonstrates strong performance across diverse benchmarks while recognizing harmful requests without needlessly blocking harmless ones.
Source: Hacker News · Summarized by HeadlinesBriefing