Lifestyle
NVIDIA Vera Rubin Debuts in MLPerf: Claims a Sweep of Training v6.1, With Over 10x Throughput per Watt on Kimi K3 (Provisional)
NVIDIA says its Vera Rubin platform posted leading results in MLPerf Training v6.1 and the debut MLPerf Endpoints, though the Vera Rubin Endpoints results are still pending MLCommons verification.
News date: About 4 min read
Contents
On November 16, 2026, NVIDIA published the first MLPerf results for its Vera Rubin platform. MLPerf is a set of AI system performance benchmarks whose results are published by the MLCommons Association. The results cover training, post-training (further tuning after a model's initial training, such as reinforcement learning) and agentic inference. Agentic inference refers to an AI agent repeatedly reasoning, calling tools and checking its work to complete a task. The Training v6.1 results are published, while the Vera Rubin results in Endpoints are provisional and pending MLCommons verification.
What results did NVIDIA announce?
NVIDIA says it was the only platform in this round to submit results on every benchmark, spanning large language models, image generation, recommendation systems and reinforcement learning post-training. MLPerf Training measures how fast systems can train various AI models to a target accuracy.
NVIDIA says Vera Rubin NVL72 made its debut with up to 2x the per-GPU performance of its previous-generation GB300 NVL72 system. NVIDIA stresses these are early results and that it will keep optimizing through the CUDA software stack. On the DeepSeek-V3 benchmark, NVIDIA says Vera Rubin NVL72 scaled from 256 to 1,024 GPUs at about 97% efficiency, cutting training time from 16 minutes to about 4 minutes.
How reliable are the MLPerf Endpoints agentic inference results?
According to NVIDIA, MLPerf Endpoints tests systems with real agentic coding and enterprise workflows and checks that the agent still completes tasks correctly. Every step of AI computation produces tokens (the basic units AI uses to process and generate content). Throughput per watt measures how much agent work a system completes for each watt of power consumed. In the provisional Kimi K3 result, NVIDIA says Vera Rubin NVL72 delivered more than 10x the throughput per watt of GB300 NVL72 at the same response speed.
NVIDIA's footnote states that the GB300 results have been verified by MLCommons, while the Vera Rubin provisional results await verification and may change with peer review. The 10x figure should therefore be treated as preliminary, vendor-published data.
| Item | Vera Rubin NVL72 | GB300 NVL72 |
|---|---|---|
| Kimi K3 accelerators | 32 | 48 |
| Concurrent queries | 1,024 | 48 |
| System throughput (tokens/sec) | 41,414.2 | 2,210.4 |
| Operating power | 100.89 kW | 60 kW |
| Verification status | Provisional, pending MLCommons verification | Verified by MLCommons |
Which partners took part, and what does it mean for ordinary users?
NVIDIA says 20 organizations submitted results to MLPerf Training, including ASUS, Azure, Cisco, CoreWeave, Dell Technologies, Google Cloud, HPE, Oracle, Supermicro and the University of Florida. NVIDIA also says it ran the round's largest test, with 10,240 GPUs on GB300 systems. NVIDIA says Microsoft Azure matched that scale, also using 10,240 GPUs, on GB200 systems.
NVIDIA's argument is that faster training gets smarter agents into users' hands sooner, while more tokens per watt in inference means power-constrained data centers can serve more agents. NVIDIA also says Vera Rubin leads on independent benchmarks such as SemiAnalysis AgentX and Artificial Analysis AgentPerf.
Frequently asked questions
Can I buy or use Vera Rubin yet?
NVIDIA's article only publishes benchmark results and does not state availability timing, pricing or regional supply, so this cannot be determined from the source.
What does "sweep" mean?
NVIDIA says its platform was the only one in this round to submit results on every MLPerf Training v6.1 benchmark, and says it swept all of them. This is NVIDIA's own characterization.
Is the 10x throughput per watt a final result?
No. NVIDIA notes the Kimi K3 Vera Rubin result is provisional, pending MLCommons verification, and may change with peer review.
Will the results change later?
NVIDIA says Vera Rubin performance will keep improving through continued optimization of the CUDA software stack, and calls the current results just the beginning.
Browse the latest news in this topic
Found this guide helpful? Share it with someone who needs it
Lifestyle
AMD Says Lux Supercomputer Is Open to Scientific Users at Oak Ridge, Ranked No. 14 on TOP500 and Built on MI355X GPUs
AMD announced that the AMD-powered, HPE-built Lux supercomputer is now open to scientific users at the US Department of Energy's Oak Ridge National Laboratory and is the first dedicated AI Factory for the Genesis Mission. AMD encourages interested users to contact OLCF.
Lifestyle
Google report: attackers use AI to find vulnerabilities from software updates and build exploits; Google introduces AI Threat Defense
Google Threat Intelligence Group (GTIG) said on November 16, 2026 that its AI Threat Tracker report found attackers using autonomous AI frameworks to analyze software updates, identify patched flaws and build exploits. Google also introduced AI Threat Defense, combining Gemini, Wiz, CodeMender and Mandiant, but gave no availability stage or pricing.
Lifestyle
NVIDIA Unveils Rubin HPC GPU: Over 50,000 CUDA Cores per Chip, Expected in 2028
At SC26, NVIDIA announced Rubin HPC, a new member of the Vera Rubin platform aimed at scientific, engineering and analytics simulation. Each GPU has over 50,000 CUDA cores, with availability expected in 2028.
Lifestyle
Google Cloud Publishes MLPerf Training v6.1 Results: 8,192 Ironwood TPUs Hit Target in 1.70 Minutes, Plus the First Agentic Reinforcement Learning Test
Google Cloud says it submitted 10 results to the MLPerf Training v6.1 AI benchmark using Ironwood TPUs and NVIDIA Grace Blackwell GPUs, covering pretraining and the first agentic reinforcement learning benchmark. This is a results announcement, not a product launch; all figures are Google's own.
Sources
Compiled from the references and verification dates listed above; fares, schedules, product features, and terms can change, so please confirm the latest details on the relevant official website before travelling, booking, or purchasing.