Nvidia's rack-scale AI computing system built around Vera Rubin GPUs, the successor to Blackwell NVL72 for large-scale AI training and inference.
Cognition says its SWE-2 model produced up to 4.8 times more total token throughput on Nvidia's Vera Rubin NVL72 than on GB200, in a test on CoreWeave. The company-run result points to more agent capacity per system, but whether long coding tasks get cheaper depends on what the new systems cost per hour.
Reality
MLPerf Inference v6.1 preview submissions put Vera Rubin NVL72 at up to 3.7x GB300 on Qwen3-VL and up to 2.5x on DeepSeek-R1, on two different inference frameworks. The four-rack 99% scaling result is an offline number.
Reality
On Alphabet's Q1 2026 call Sundar Pichai put cloud backlog above $460 billion, close to six years of cloud revenue at the current rate, while giving Gemini Enterprise's paid user base as a growth rate alone.
Reality
SemiAnalysis says its AgentX benchmark clocked Nvidia's Vera Rubin NVL72 at up to seven times Blackwell's token throughput per megawatt on pre-release software, and puts the profit gain at over two times per gigawatt.
Reality
NVHBM offers NVLink Fusion partners 30 percent more bandwidth and 15 percent less power, in exchange for NVIDIA owning the interface between their compute and their memory.
Perspective Coverage
3 publishersReality
The zettaFLOPS figure is an estimate. The measured one, sitting in a GB300 example, is a 25 percent density gain, and it is paid for out of the safety margin.
Reality
The first third-party benchmark of the LP30 rack came in at roughly four times the next-fastest public endpoint, measured one request at a time on a model small enough to fit.
Reality
SemiAnalysis has pushed fixed-length serving into maintenance mode. On replayed Claude Code traffic, NVIDIA's GB300 is credited with 15x Hopper, against 40x over H200 on the retired static test.
Reality