Technology / 17 Nov 2026
Vera Rubin's 10x claim
NVIDIA says its Vera Rubin platform swept every MLPerf Training v6.1 benchmark and, in its first MLPerf Endpoints submission, posted more than 10x generational gains in throughput per watt for agentic AI.
Sources.
NVIDIA Sweeps MLPerf Training and Endpoints as Vera Rubin Debuts With Leading Performance | NVIDIA Blogblogs.nvidia.comMedia credits.
No external media credits were recorded.
Context and limitations.
These are NVIDIA's own claims published in its blog. The 10x Kimi K3 figure is a provisional result, and the 2x figure is described as early. Attribute the numbers to NVIDIA and avoid presenting them as independent verification.