NVIDIA Vera Rubin NVL72 at a glance
In MLPerf results released November 16, 2026, NVIDIA Vera Rubin NVL72 debuted by sweeping every MLPerf Training v6.1 benchmark at up to 2x the performance per GPU of GB300 NVL72, and led MLPerf Endpoints with more than 10x the throughput per watt for agentic AI.
Ask your AI about this story
Use this story in your business: NVIDIA Vera Rubin sweeps MLPerf Training v6.1 and leads MLPerf Endpoints in its debut (NVIDIA). Ask your AI to explain what happened, how it could affect your business and how to put it to work. It also weighs price, speed, intelligence and the lab behind it. The link to the story is included.
What changed with NVIDIA Vera Rubin NVL72
NVIDIA's Vera Rubin platform made its MLPerf debut in results released on November 16, 2026, sweeping every MLPerf Training v6.1 benchmark: NVIDIA was the only platform with results on every test, spanning large language models, image generation, recommender systems and reinforcement-learning post-training. Vera Rubin NVL72 delivered up to 2x more performance per GPU than the GB300 NVL72 system, and on the DeepSeek-V3 benchmark it scaled from 256 to 1,024 GPUs at about 97% efficiency, cutting the training time from 16 minutes to about four.
In its first MLPerf Endpoints submission, which tests systems on agentic coding and enterprise workflows and checks that agents still complete their tasks, Vera Rubin led across all of its agentic benchmarks. In a provisional result on Kimi K3 published November 9, 2026, Vera Rubin NVL72 delivered more than 10x the throughput per watt of GB300 NVL72 at the same response speed; NVIDIA notes the provisional Vera Rubin Endpoints results are pending MLCommons verification and peer review. Google Cloud published 10 MLPerf Training v6.1 results the same day, on seventh-generation Ironwood TPUs and Grace Blackwell GPUs, including the round's first agentic reinforcement-learning benchmark.
NVIDIA Vera Rubin NVL72 in numbers
Values are copied from the linked source on the date shown. They are not IA Compa measurements.
- Performance per GPU vs GB300 NVL72 (MLPerf Training v6.1)as of · Source for Performance per GPU vs GB300 NVL72 (MLPerf Training v6.1): blogs.nvidia.com (opens in a new tab)
- Up to 2x per GPU
- Throughput per watt vs GB300 NVL72 (MLPerf Endpoints, Kimi K3)as of · Source for Throughput per watt vs GB300 NVL72 (MLPerf Endpoints, Kimi K3): blogs.nvidia.com (opens in a new tab)
- More than 10x per watt (provisional)
Where to compare NVIDIA Vera Rubin NVL72
Independent leaderboards and official resources for comparing this model yourself. Rankings change often; each site shows its own current data.
Leaderboards
General leaderboards
Official resources
Why NVIDIA Vera Rubin NVL72 matters for businesses
Why it matters: businesses that serve AI agents are limited by data-center power, so Vera Rubin's throughput per watt on agentic workloads translates directly into how many agents a facility can serve for each unit of electricity it can buy. The dated MLPerf Training v6.1 and Endpoints numbers also give infrastructure buyers an independent yardstick for comparing NVIDIA, Google and other platforms before committing to a generation of hardware.
Put it to work: AI services
Get AI News by email
Verified AI stories, each with its official source, on Monday and Thursday mornings. Add breaking news to hear about the biggest ones as soon as we publish them.
Every story links its official source
Free, in English or Spanish
Unsubscribe with one click, any time
Sources for this story
- NVIDIA Sweeps MLPerf Training and Endpoints as Vera Rubin Debuts With Leading Performance (opens in a new tab)Official
NVIDIA Blog · blogs.nvidia.com
- MLPerf Training v6.1 and Endpoints v1.0 results (opens in a new tab)Benchmark
MLCommons · mlcommons.org
Last verified: . IA Compa summarizes public announcements for business readers. We are not affiliated with the companies mentioned. Always confirm details, pricing, and availability with the official source.
- #nvidia
- #vera-rubin
- #mlperf
- #benchmarks
- #ai-infrastructure
- #inference

