# 微软发布 MAI-Thinking-1 模型

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-06-03 04:51
- AIHOT 分数：81
- AIHOT 链接：https://aihot.virxact.com/items/cmpx50j2000omslckjh7fnc75
- 原文链接：https://x.com/rohanpaul_ai/status/2061913509399789924

## AI 摘要

微软发布了 MAI-Thinking-1，这是一款采用 MoE 架构的模型，拥有 35B 活跃参数和 1T 总参数。该模型从零开始在 30T tokens 上完成预训练，且未使用第三方模型蒸馏。微软称其迭代优化流程为“爬山机器”。在基准测试中，该模型于 AIME 2025 获得 97.0%，在 LiveCodeBench v6 获得 87.7%，在 SWE-Bench Pro 获得 52.8% 的成绩。

## 正文

Microsoft unveiled MAI-Thinking-1.

So Microsoft now has a full in-house pipeline for building stronger reasoning models again and again.

Microsoft calls this system a "hill-climbing machine," meaning it keeps improving the data, training setup, rewards, safety tests, and evaluations as one connected process.

Strong for its size, including 97.0% on AIME 2025, 87.7% on LiveCodeBench v6, and 52.8% on SWE-Bench Pro.

MAI-Thinking-1 is the first model from that process, using 35B active parameters inside a 1T total parameter mixture-of-experts model, where only part of the model runs for each token.

The base model was trained from scratch on 30T mostly human-generated tokens, with Microsoft saying it avoided third-party model distillation during pre-training.

After that, the team used reinforcement learning, which means the model practiced tasks and improved from feedback, to teach math reasoning, coding, tool use, helpfulness, and safety.