Microsoft-Decision-1

Product Hunt Models
decision-scoring agent-workflows classification routing microsoft-foundry qwen structured-output

Summary

Microsoft 推出 Decision-1 决策打分模型，用于代理与工作流的路由、分类、验证和控制，单次推理即可输出各选项的校准概率。该模型基于 Qwen3.5-9B 后训练，据称中位延迟比 GPT-6 Sol 快约 35 倍，现已在 Microsoft Foundry 上线。

<p> Microsoft’s decision model for agents and workflows </p> <p> <a href="https://www.producthunt.com/products/microsoft-decision-1?utm_campaign=producthunt-atom-posts-feed&amp;utm_medium=rss-feed&amp;utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1275196?app_id=339">Link</a> </p>
Original Article
View Cached Full Text

Cached at: 10/10/26, 08:32 AM

# Microsoft-Decision-1: Microsoft’s decision model for agents and workflows | Product Hunt Source: [https://www.producthunt.com/products/microsoft-decision-1](https://www.producthunt.com/products/microsoft-decision-1) Microsoft\-Decision\-1 is a decision\-scoring model for routing, classification, verification and agent control\. Give it fixed options and it returns a calibrated probability for each in a single pass, as structured output software can act on directly\. Post\-trained from Qwen3\.5\-9B, it is about 35x faster than GPT\-6 Sol at median latency, per Microsoft\. Available now in Microsoft Foundry at $0\.042 per million input tokens, with free output\.

Similar Articles

Microsoft-Decision-1, our model for fast decision-making

Hacker News Top

微软发布 Microsoft-Decision-1，一个专为快速决策打分设计的模型，可用于路由、分类、优先级排序与工作流控制，基于 Qwen3.5-9B 后训练，在 36 项基准测试中取得最高准确率，延迟比 GPT-6 Sol 快约 35 倍。

vllm-sr/d3

Hugging Face Models Trending

vllm-sr/d3 是 Decision 3.0 的 27B 多模态基础决策模型，支持文本、JSON、图像与视频输入，可在一次调用中完成选择、是非与评分决策并输出概率，无需生成文本。它在 Jev Decision Index 上以 66.3 排名官方文本榜第一，较 Decision 2.0 提升 10.4，并在 AMD MI325X 上实现 27 req/s 的服务性能。

@wlzh: Microsoft + UPenn Open-Source Multiplex Thinking: Let LLMs 'Clone' at Forks Then Merge. In a nutshell: When reasoning reaches a critical decision point, the model 'clones' into K pathfinders, each taking a different path. After one step, they merge back into a composite token and continue. With K=3, one token carries the information of three…

X AI KOLs Timeline

Microsoft and the University of Pennsylvania open-source Multiplex Thinking, which allows LLMs to split into K parallel paths during inference, explore, then merge, improving efficiency. On a 7B model, it achieves over 50% accuracy on AMC2023 (first 7B model to do so) and over 55% on AIME2025.

@yibie: https://x.com/yibie/status/2104076142500069608

X AI KOLs Timeline

This article demonstrates how to convert GLM-5.3-Flash into a Jev-style System 1 decision model, achieving typed decisions through a single forward pass. Benchmark tests show that it performs comparably to specialized models in terms of accuracy and speed.