Microsoft-Decision-1

Calibrated confidence means that when the system gives a score of 0.9, the probability of being correct should be close to 90%.

The way Decision-1 is used is to give it a fixed set of candidate options, and it returns calibrated probability values for each option in a single inference pass.

Microsoft launched Microsoft-Decision-1 on Product Hunt, a decision scoring model specifically designed for decision-making.

Microsoft reported that Decision-1 achieved the highest accuracy in a comparison across 36 benchmarks covering nearly 150,000 questions, and claimed its P50 latency is approximately 35 times faster than GPT-6 Sol.

The Xbox research team used Decision-1 to categorize over 10,000 pieces of feedback, achieving performance comparable to GPT-6 Sol but more than 14 times faster and 200 times cheaper.

d1-3B's question types include noul (returns P(yes)), choice (returns the selected option, confidence, and the probability of each option), and score (returns the expected rating, confidence, and probability distribution on a 2–10 ordinal scale).

According to the original text, in late 2026 a batch of commercial System One decision models (such as TypeSafe Jev and Microsoft-Decision-1) began selling typed decision primitives (binary gates, closed-set choices, ordinal scores) as product APIs.

Microsoft's Microsoft-Decision-1 and TypeSafe AI's Jev have already commercialized decision models based on the Decision Head architecture.

Microsoft's Microsoft-Decision-1 claims a decision speed 35 times faster than GPT-6, and its base model is Alibaba's open-source Qwen3.5-9B.

The choice type always selects one option, and if no abstention option is provided, the model is forced to give an answer even when evidence is insufficient; the Learn documentation recommends adding an abstention option when a choice should not be forced.

The endpoint path for Microsoft-Decision-1 on Foundry is <your-foundry-resource-endpoint>/providers/microsoft/v1/systemone, and the model field in the request is filled with the deployment name rather than the model string.

OpenRouter lists Microsoft-Decision-1's context window as 32,768 tokens, with text-only input and structured decision output, and no support for images or audio.

A Microsoft-Decision-1 request is not a chat completion; it requires passing in state (a string or JSON) plus named questions.

The model ID for Microsoft-Decision-1 on OpenRouter is microsoft/microsoft-decision-1, and the official documentation states that the chat-completions SDK cannot be used and the Decisions / System One interface must be used instead.

The balance between speed and quality in specialized decision models attempts to make trade-offs between two metrics that often conflict with each other.

Embedding a decision model into incident response workflows can automate the first two steps of the 'alert triage → root cause localization → remediation matching' pipeline.

Decision-1 is not designed for open-ended dialogue or text generation, but is specifically optimized for structured decision-making tasks.

Microsoft claims that Decision-1 outperforms general-purpose large language models and other specialized decision models on structured decision-making tasks across both the latency and quality dimensions.

Microsoft has not yet publicly disclosed Decision-1's specific architecture, parameter scale, training methodology, or quantifiable benchmark data.

Microsoft-Decision-1 outperforms traditional large language models and decision models such as Jev 1.13.0 on metrics including latency and accuracy