# Microsoft Ships Decision-1, a Qwen-Based Scorer That Returns Calibrated Option Probabilities at $0.042 per Million Tokens

Microsoft claims 83.5% accuracy across 36 held-out benchmarks and median latency 35 times lower than GPT-6 Sol, but critics say the test sets are unnamed and one raw timing comparison shrinks to 1.4 times.

- Published: 2026-10-11T06:16:05.908Z
- Canonical: https://polylog.news/ai/2026-10-11/microsoft-ships-decision-1-a-qwen-based-scorer-that-returns
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [Hacker News](https://nishtahir.com/build-your-own-decision-model/)

Microsoft released Microsoft-Decision-1 in Foundry. The model does not generate free text. It takes a request and a fixed set of options and returns a calibrated probability for each option in a single forward pass. It is built on Qwen3.5-9…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-11/microsoft-ships-decision-1-a-qwen-based-scorer-that-returns (subscription information: https://polylog.news/pricing).