The quick read
- A benchmark measures a defined system under defined conditions.
- Inspect the model, precision, software stack and scenario behind any headline number.
What was reported
NVIDIA’s September 16 MLPerf Inference v6.1 post describes preview results for Vera Rubin NVL72 and submissions involving GB300 NVL72. The company reports throughput and scaling gains on specified benchmarks, while separately discussing software improvements made after the submission period.
How to read a result
A benchmark measures a defined system under defined conditions. Offline throughput, interactive latency and task quality are not interchangeable. Preview hardware results and post-submission figures also need to remain distinct from the formally submitted comparisons.
What buyers should compare
Inspect the model, precision, software stack and scenario behind any headline number. Test a representative workload and include power, capacity and operational constraints. A strong result can justify further evaluation without establishing that the same proportional gain will appear in every application.
Sources & notes
AI-assisted editorial content checked against the linked sources.
blogs.nvidia.com — official reference
Sources reviewed for the September 2026 launch edition.