# Microsoft releases Microsoft-Decision-1, a Qwen3.5-9B-based scoring model

Digest AI · Generative AI & Models · published 2026-10-10T06:03:09Z · updated 2026-10-12T22:53:00Z

Canonical: https://digestai.news/story/microsoft-releases-microsoft-decision-1-a-qwen3-5-9b-based-scoring-mod

## Summary

Microsoft has launched Microsoft-Decision-1, a specialized model designed for routing, classification, and agent control. Unlike standard language models that generate text, this tool returns calibrated probabilities for fixed answer options. It is post-trained from Alibaba’s Qwen3.5-9B and is currently available via Microsoft Foundry and OpenRouter. The model features a 32,768-token context window and operates exclusively through a hosted API, with no open weights or quantized variants released.

Microsoft reports that the model achieved an average accuracy of 83.5% across 36 internal benchmarks, outperforming Quyet-1.0-Large at 81.9%. It also demonstrated a p50 latency of 85 ms, which Microsoft claims is 4.5 times faster than Quyet-1.0-Large and 35 times faster than GPT-6 Sol. However, the latency comparison is disputed by H2O.ai, which argues that Microsoft’s use of JevBench adjusted medians inflates competitor times. Independent verification on the JevBench board is still pending, where H2O-Lightning-4B currently ranks first.

Pricing is set at $0.042 per million input tokens, with output tokens free. The model is restricted to text-only inputs and cannot handle images, audio, or video. It is explicitly not designed for text generation, open-ended Q&A, or sole automated decisions in sensitive areas like credit or employment. Developers must define specific options and thresholds for use.

## Key points

- Microsoft-Decision-1 is post-trained from Qwen3.5-9B and returns probabilities for fixed options.
- Microsoft reports 83.5% average accuracy and 85 ms p50 latency across 36 internal benchmarks.
- The model costs $0.042 per million input tokens with free output, available via API only.

## Why it matters

This release targets high-volume, low-latency decision tasks where text generation is unnecessary. By offering calibrated probabilities at a lower cost than general-purpose LLMs, it provides a specialized tool for agent control and routing in enterprise applications.

## Sources

1. [Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model](https://marktechpost.com/2026/10/09/microsoft-ai-releases-microsoft-decision-1-a-qwen3-5-9b-decision-scoring-model) (MarkTechPost, 2026-10-10)
2. [Microsoft separates decision-making from generative AI with a new model](https://infoworld.com/article/4234290/microsoft-separates-decision-making-from-generative-ai-with-a-new-model.html) (infoworld.com, 2026-10-12)

Part of the developing story: [The Rise of Self Managing AI Models](https://digestai.news/thread/researchers-introduce-context-language-models-that-manage-their-own-context) (2 stories)

## Cite

Digest AI, "Microsoft releases Microsoft-Decision-1, a Qwen3.5-9B-based scoring model", 10 October 2026, https://digestai.news/story/microsoft-releases-microsoft-decision-1-a-qwen3-5-9b-based-scoring-mod

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/microsoft-releases-microsoft-decision-1-a-qwen3-5-9b-based-scoring-mod.json