{"version":1,"type":"story","url":"https://digestai.news/story/microsoft-releases-microsoft-decision-1-a-qwen3-5-9b-based-scoring-mod","json":"https://digestai.news/story/microsoft-releases-microsoft-decision-1-a-qwen3-5-9b-based-scoring-mod.json","markdown":"https://digestai.news/story/microsoft-releases-microsoft-decision-1-a-qwen3-5-9b-based-scoring-mod.md","slug":"microsoft-releases-microsoft-decision-1-a-qwen3-5-9b-based-scoring-mod","headline":"Microsoft releases Microsoft-Decision-1, a Qwen3.5-9B-based scoring model","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.\n\nMicrosoft 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.\n\nPricing 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.","keyPoints":["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."],"whyItMatters":"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.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Microsoft","Alibaba","OpenRouter","H2O.ai","OpenAI"],"models":["Microsoft-Decision-1","Qwen3.5-9B","Quyet-1.0-Large","GPT-6 Sol","GPT5.6 Luna","H2O-Lightning-4B"],"people":[]},"firstPublishedAt":"2026-10-10T06:03:09Z","updatedAt":"2026-10-12T22:53:00Z","sourceCount":2,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model","url":"https://marktechpost.com/2026/10/09/microsoft-ai-releases-microsoft-decision-1-a-qwen3-5-9b-decision-scoring-model","publishedAt":"2026-10-10T06:03:09Z","type":"press","primary":false,"lead":true},{"outlet":"infoworld.com","title":"Microsoft separates decision-making from generative AI with a new model","url":"https://infoworld.com/article/4234290/microsoft-separates-decision-making-from-generative-ai-with-a-new-model.html","publishedAt":"2026-10-12T22:53:00Z","type":"press","primary":false,"lead":false}],"sourceNotes":null,"discussions":[],"thread":{"title":"The Rise of Self Managing AI Models","url":"https://digestai.news/thread/researchers-introduce-context-language-models-that-manage-their-own-context","storyCount":2},"cite":{"text":"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","publisher":"Digest AI","title":"Microsoft releases Microsoft-Decision-1, a Qwen3.5-9B-based scoring model","datePublished":"2026-10-10T06:03:09Z","url":"https://digestai.news/story/microsoft-releases-microsoft-decision-1-a-qwen3-5-9b-based-scoring-mod"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"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"}