Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model
Microsoft has released Microsoft-Decision-1, a decision model for routing, classification, verification and agent control. Microsoft-Decision-1 is a decision-scoring model that returns a calibrated probability for each fixed answer option instead of generated text. It is post-trained from Alibaba’s Qwen3.5-9B and available now in Microsoft Foundry and OpenRouter. . TL;DR Size: Built on Qwen3.5-9B; exact parameter count not disclosed. 32,768-token context window. Runs on: Hosted
Get smart on it
Microsoft released a decision-scoring model that evaluates a fixed set of answer options and returns probability scores rather than generating text. This type of model is designed for tasks like routing, classification, and agent control where software needs to act immediately on the results. The model achieved the highest average accuracy across 36 benchmarks at 83.5 percent while operating significantly faster than comparable systems, making it suitable for applications that require quick, calibrated decisions at lower cost than alternative options.
Related news
TII Releases Falcon-ASR: 1.6B Arabic Speech Model Hits 20.92% WER
The Technology Innovation Institute (TII) in Abu Dhabi has released Falcon-ASR, a 1.6B parameter Arabic speech recognition model. It focuses on the Emirati dialect and also transcribes English, French, Spanish and Portuguese. In TII’s evaluation, Falcon-ASR posts a 20.92% average word error rate (WER) across 6 Arabic test sets. That beats the best published entry in TII’s leaderboard snapshot by 2.25 points. For developers building Arabic voice products, the catch is access: today i
What is Decision 3.0? vLLM Semantic Router’s New Open Decision Models
The vLLM Semantic Router team has released Decision 3.0, a family of multimodal decision models. Decision 3.0 multimodal decision models read text, JSON and images, then answer typed questions about them. There are 5 sizes, from 0.8B to 27B, all under Apache-2.0. For developers, this is a fast way to classify, route and gate requests without parsing generated text. TL;DR Size: 5 models: d3-lite (0.85B), d3-nano (2.21B), d3-mini (4.54B), d3-flash (8.39B), d3 (26.09B). Context length: not
