Today ainotis Join

My notis

ModelsPublished All news from that day

Ongoing case: Typed decision models and APIs New model · 4 stories

Microsoft released Microsoft-Decision-1, a model that scores answer options, in Foundry and through OpenRouter.

Microsoft says the model is available in Foundry and through OpenRouter, and in its own tests was 35 times quicker than GPT-6 Sol.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

Share

Check our sources · 11 facts from 1 source

Microsoft introduced Microsoft-Decision-1 on 9 October 2026 on its Command Line blog. It is a model for fast decision-scoring, available in Microsoft Foundry and through OpenRouter, and is meant for routing, classification, prioritization, verification and workflow control.

Given a fixed set of answer options, it returns a calibrated probability score for each option, and it supports yes/no, multiple-choice and rating options as well as rubric-based grading of AI responses and agent actions.

Microsoft says it post-trained Qwen3.5-9B to build the model and will soon rebase it on other models, including Microsoft AI (MAI) and OpenAI models. Input tokens cost $0.042 per million, and output tokens are free.

The figures are Microsoft's own. It says the model had the highest accuracy in a comparison across 36 benchmarks and nearly 150,000 questions, and was the fastest measured: 2.5 times quicker than H2O-Lightning-4B v1.1, the runner-up, and 35 times quicker than GPT-6 Sol.

It says the model changes its decision on 1.3% of perturbed inputs on average.

Microsoft also describes internal use: Xbox Research sorted more than 10,000 open-ended pieces of feedback and reviews into a fixed set of themes and found the model competitive on quality with GPT-6 Sol while running over 14 times faster and 200 times less expensive.

Share this story

Your reaction

We count reactions per story and day, never who reacted. The counts help us choose what goes in the monthly issue. If you are signed in, your own page shows yours too.

Check our sources

Every sentence above is checked against this source.

1 Introducing Microsoft-Decision-1, our model for fast decision-makingMicrosoft Command Line · 9 Oct 2026 · 11 facts Open the source archived copy

  1. Microsoft published the post "Introducing Microsoft-Decision-1, our model for fast decision-making" on 9 October 2026 (dated 2026.10.09), written by Achint Srivastava, Vice President of Software Engineering in the Office of the CTO.

    Introducing Microsoft-Decision-1, our model for fast decision-making / By Achint Srivastava / VP of Software Engineering, Office of the CTO, Microsoft / 2026.10.09
    cite

  2. Microsoft says: "Today we’re introducing Microsoft-Decision-1, our new model for fast decision-scoring, available in Microsoft Foundry and through OpenRouter."

    Today we’re introducing Microsoft-Decision-1, our new model for fast decision-scoring, available in Microsoft Foundry and through OpenRouter.
    cite

  3. Microsoft says the model "is designed for routing, classification, prioritization, verification, and workflow control".

    designed for routing, classification, prioritization, verification, and workflow control
    cite

  4. Microsoft says: "When given a fixed set of answer options, Microsoft-Decision-1 provides a calibrated probability score for each option."

    When given a fixed set of answer options, Microsoft-Decision-1 provides a calibrated probability score for each option.
    cite

  5. Microsoft says the model "supports yes/no, multiple-choice, and rating options, as well as rubric-based grading of AI responses and agent actions".

    The model supports yes/no, multiple-choice, and rating options
    cite

  6. Microsoft says: "we post trained Qwen3.5-9B for fast, single-pass decision scoring and will soon rebase it on other models, including Microsoft AI (MAI) and OpenAI."

    we post trained Qwen3.5-9B for fast, single-pass decision scoring
    cite

  7. Microsoft's pricing section says: "Input tokens cost $0.042 USD per million tokens. Output tokens are free."

    Input tokens cost $0.042 USD per million tokens. Output tokens are free.
    cite

  8. Microsoft says: "Microsoft-Decision-1 achieved the highest accuracy in our 36-benchmark comparison, spanning nearly 150,000 questions across benchmarks kept blind from training."

    achieved the highest accuracy in our 36-benchmark comparison, spanning nearly 150,000 questions
    cite

  9. Microsoft says that in its benchmarking the model "was the fastest measured: 2.5 times quicker than H2O-Lightning-4B v1.1, the runner-up, and 35 times quicker than GPT-6 Sol".

    it was the fastest measured: 2.5 times quicker than H2O-Lightning-4B v1.1, the runner-up
    cite

  10. Microsoft says: "Microsoft-Decision-1 changes its decision on 1.3% of perturbations on average", from perturbing the same request in eight ways.

    We perturb the same request in eight ways and measure how often the decision flips. Microsoft-Decision-1 changes its decision on 1.3% of perturbations on average
    cite

  11. Microsoft says XBOX Research used the model to process more than 10,000 open-ended pieces of feedback and reviews and sort them into a fixed set of themes, and found it "to be competitive on quality with GPT-6 Sol while running over 14 times faster and 200 times less expensive".

    They found Microsoft-Decision-1 to be competitive on quality with GPT-6 Sol while running over 14 times faster and 200 times less expensive.
    cite

Topics

The morning email

On the mornings we publish: the three top stories and up to four short ones. Free.

We email you a link to confirm. An issue may include one sponsor, always labelled Sponsored · Advertisement. Our emails count opens and clicks, not who made them. Unsubscribe in one click. What we keep