Microsoft releases Decision-1, a decision model built on Qwen3.5-9B that it says beats Jev

Microsoft has released Decision-1, its own decision model for fast, structured choices such as classifications, evaluations and routing decisions. Microsoft says the model has "the potential" to guide and control agents through complex environments. Decision-1 is based on Alibaba's open-weight Qwen3.5-9B, and The Register reports that Microsoft says the next version will use its own technology. Microsoft says Decision-1 was the most accurate model across 36 benchmarks covering nearly 150,000 questions. Its chart shows 83.5 percent accuracy and 85 milliseconds of latency, ahead of Jev 1.13.0. Microsoft also says the model is 2.5 times faster than the runner-up, H2O-Lightning-4B. Cloudflare's open-source Clef models, which are also based on Qwen, were not included in the comparison. Decision-1 is available through Microsoft Foundry and OpenRouter. Input tokens cost $0.042 per million, and output tokens are free. The category was started by TypeSafe AI's Jev, released in mid-September. Decision models give constrained answers rated by probability, which makes them suited to business uses where open-ended text is undesirable. With Microsoft joining OpenAI and Cloudflare, The Decoder notes that small open models were quickly adapted to match or surpass the original.