Microsoft's Decision-1 model enters the fast-growing AI decision model race

The Decoder 10 Oct 2026, 14:57 UTC 1 min read

In brief

Microsoft has introduced Decision-1, a compact model designed for classification, evaluation and routing tasks, including potential control of AI agents in complex environments. The company says it leads its tested comparison on accuracy and speed, and has released it through Microsoft Foundry and OpenRouter.

Decision-1 is based on Qwen3.5-9B and was evaluated across 36 benchmarks containing nearly 150,000 questions.

Microsoft reports 83.5% accuracy and 85 ms latency, with performance 2.5 times faster than H2O-Lightning-4B, the next-fastest model in its comparison.

Input pricing is $0.042 per million tokens; output tokens are free.

Cloudflare’s Qwen-based Clef models were not included in the comparison.

Why it matters: The launch adds Microsoft to a rapidly expanding market for small, low-latency models intended to make operational decisions for AI systems.

Editorial brief by Sakhanda Wire AI, based on reporting by The Decoder.

Microsoft's Decision-1 model enters the fast-growing AI decision model race

Matthias Bastian View the LinkedIn Profile of Matthias Bastian

Oct 10, 2026

Microsoft now has its own decision model. Like the ones from OpenAI, Cloudflare, and the "original" from Jev, Decision-1 is built for fast, structured decisions. According to Microsoft, it handles classifications, evaluations, and routing decisions and has "the potential" to "guide and control agents through complex environments."

Decision-1 is based on Qwen3.5-9B. Microsoft says it's the most accurate model tested across 36 benchmarks covering nearly 150,000 questions. On speed, it's 2.5 times faster than the runner-up, H2O-Lightning-4B. Cloudflare's open-source Clef models, which are also based on Qwen, weren't included in the comparison.

Microsoft's benchmark comparison puts Decision-1 at the top with 83.5% accuracy and 85 ms latency, ahead of Jev 1.13.0. | Image: Microsoft

Decision-1 is available through Microsoft Foundry and OpenRouter. Input tokens cost $0.042 per million, and output tokens are free. Jev, the startup that kicked off the decision model trend in mid-September, has likely had a rough few weeks. The idea caught on fast, but the tech was quickly adapted and surpassed using open small language models.

AI News Without the Hype – Curated by Humans

Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.

Source: Microsoft

Microsoft's Decision-1 model enters the fast-growing AI decision model race

AI News Without the Hype – Curated by Humans

More stories