# Microsoft claims higher training efficiency for MAI-Base-2

_Published Thursday, October 15, 2026 at 11:42 PM EDT · AI · Latest · Tier 2 — Notable_

Microsoft unveiled MAI-Base-2, claiming 4x-12x greater pretraining efficiency measured in floating-point operations than DeepSeek-V4-Pro-Base. The mixture-of-experts model has 2.8T total parameters and activates 80B, using a subset of its parameters for computation. The efficiency comparison is Microsoft's claim.

## Sources

- [Techmeme](https://www.techmeme.com/261015/p59#a261015p59)

---
Canonical: https://techandbusiness.org/newswire/3llE9MkczNmAPOleceH9Fr
Published: 2026-10-16T03:42:10.656Z
Story chronology: 2026-10-16T02:20:01.000Z
Retrieved: 2026-10-16T06:30:07.992Z
Publisher: Tech & Business (techandbusiness.org)