← Saturday, October 17, 2026Models & trainingRelease

Microsoft says MAI-Base-2 uses 4–12× fewer pretraining FLOPs than an open base model

microsoft.ai 13 min read Editor score 8/10

Microsoft says its 80-billion-active-parameter MoE model outperforms the open-weight models it tested and used 4–12× fewer pretraining FLOPs than DeepSeek-V4-Pro-Base. The efficiency comparison and evaluation claims are directly relevant to large-model training trade-offs.

What

MAI-Base-2 is an MoE foundation model with 80 billion active and 2.8 trillion total parameters.

How

Microsoft says it outperforms every open-weight model tested on held-out evaluations and uses 4–12× fewer pretraining FLOPs than DeepSeek-V4-Pro-Base.

Why it matters

Microsoft says it put the FLOP savings into training a larger model, showing how efficiency gains can be reinvested in model scale.

Read on microsoft.ai → Hacker News · 4 comments

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.