Interconnecting Intelligence The facts on AI, from demand to buildout.

ChipsData release

NVIDIA Vera Rubin NVL72 delivers more than 10x throughput per watt of GB300 NVL72 on MLPerf Endpoints Kimi K3

In a provisional result for Kimi K3 at the same response speed, Vera Rubin NVL72 outperforms GB300 NVL72 in agentic throughput per watt. It is NVIDIA's first MLPerf Endpoints submission, and the Vera Rubin results are pending MLCommons verification.

Companies
NVIDIA
Source
Nvidia news post, published Nov 16, 2026
Published here

Download share image

This fact was extracted from the source above and checked automatically: every number and company named here appears in it. When the same fact turns up in another filing or post, that source is added here instead of a second copy. Read the original before relying on it.