---
format: "aidr-story-markdown/v1"
id: "c639d63a1f698545191cfa4e4b150bab5d290854102cde81fcb93b765a5c6204"
canonical_url: "https://aidr.today/c639d63a?lang=en"
title: "NVIDIA Vera Rubin NVL72 Achieves up to 2x Blackwell Ultra Performance in MLPerf Training v6.1"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-16T16:00:00.000Z"
category: "Chips"
topics: ["nvidia","llm","agent","inference"]
source_urls: ["https://developer.nvidia.com/blog/nvidia-vera-rubin-nvl72-achieves-up-to-2x-blackwell-ultra-performance-in-mlperf-training-v6-1/","https://developer.nvidia.com/blog/nvidia-vera-rubin-nvl72-leads-agentic-inference-performance-on-mlperf-endpoints-v1-0/","https://blogs.nvidia.com/blog/mlperf-training-endpoints-vera-rubin/"]
summary: "In MLPerf Training v6.1, the NVIDIA Vera Rubin NVL72 platform achieved up to 2x more performance than a highly optimized NVIDIA GB300 NVL72 baseline. The Vera Rubin architecture delivered the fastest time to train on six of the seven benchmarks and maintained above 97% overall efficiency when scaling from 256 to 1,024 GPUs."
---

# NVIDIA Vera Rubin NVL72 Achieves up to 2x Blackwell Ultra Performance in MLPerf Training v6\.1

> [Open the canonical story](<https://aidr.today/c639d63a?lang=en>)

**Published:** 2026-11-16T16:00:00.000Z
**Category:** Chips
**Topics:** nvidia, llm, agent, inference

## Summary

In MLPerf Training v6\.1, the NVIDIA Vera Rubin NVL72 platform achieved up to 2x more performance than a highly optimized NVIDIA GB300 NVL72 baseline\. The Vera Rubin architecture delivered the fastest time to train on six of the seven benchmarks and maintained above 97% overall efficiency when scaling from 256 to 1,024 GPUs\.

## Sources

- [Story source](<https://developer.nvidia.com/blog/nvidia-vera-rubin-nvl72-achieves-up-to-2x-blackwell-ultra-performance-in-mlperf-training-v6-1/>)
- [Story source](<https://developer.nvidia.com/blog/nvidia-vera-rubin-nvl72-leads-agentic-inference-performance-on-mlperf-endpoints-v1-0/>)
- [Story source](<https://blogs.nvidia.com/blog/mlperf-training-endpoints-vera-rubin/>)

