Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B

Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model

Microsoft has released Microsoft-Decision-1, a decision model designed for routing, classification, verification, and agent control tasks. Rather than generating text, Microsoft-Decision-1 is a decision-scoring model that returns a calibrated probability for each fixed answer option—making it well suited for scenarios where deterministic, confidence-aware outputs matter more than free-form generation.

The model is post-trained from Alibaba's Qwen3.5-9B and is available now in Microsoft Foundry and OpenRouter. In the broader 2026 landscape, where agentic AI systems increasingly require reliable low-latency decision layers, this release positions Microsoft against a growing field of specialized decision and routing models.

TL;DR

• Size: Built on Qwen3.5-9B; exact parameter count not disclosed. 32,768-token context window.
• Runs on: Hosted API only (Microsoft Foundry, OpenRouter via Azure). No open weights, no quantized variants, hardware not disclosed.
• Performance: Highest average accuracy in Microsoft's 36-benchmark comparison, at 85 ms p50 latency.
• Best: 83.5% average accuracy across 36 benchmarks, ahead of Quyet-1.0-Large at 81.9%.
• Worst: Calibration of 92.2, second to Quyet-1.0-Large.

via MarkTechPost