Microsoft's Decision-1 refuses to write a single word — and that's the point
Microsoft Decision-1: 9B Qwen Model Launch Explained
Microsoft-Decision-1 is a 9-billion-parameter model built on Alibaba's Qwen3.5-9B that skips open-ended text entirely: it scores a fixed list of answer options in one forward pass and returns a calibrated probability for each. Microsoft pitches it for routing, classification, prioritization, and verification, claims 83.5% accuracy across 36 benchmarks, and lists it on OpenRouter at $0.042 per million input tokens with free output. The company says it will rebase the model on MAI and OpenAI foundations later.
To build Microsoft-Decision-1, we post trained Qwen3.5-9B for fast, single-pass decision scoring and will soon rebase it on other models, including Microsoft AI (MAI) and OpenAI.