Skip to content
View original post on X: Artificial AnalysisOfficial
Published
40/100

NVIDIA submits updated Vera Rubin configs for DeepSeek V4.1 Flash benchmarks

AINVIDIA has submitted updated Vera Rubin NVL72 configurations for DeepSeek V4.1 Flash to Artificial Analysis. Per GPU, Vera Rubin delivers 5.0x GB300's throughput at 260 tok/s per agent and 1.7x at 80 tok/s per agent.
Artificial AnalysisVerified on XOfficial
@ArtificialAnlys
View on X

Part of a thread · earlier post

NVIDIA has also submitted updated Vera Rubin NVL72 configs for DeepSeek V4.1 Flash. Against GB300’s improved results:

➤ At 260 tok/s per agent, Vera Rubin delivers 5.0x GB300’s throughput per GPU

➤ At 80 tok/s per agent, 1.7x

➤ 1 agent: 1,249 tok/s, vs 848 on GB300 (1.47x)

Source details

Artificial Analysis · x.comPublished · added here

Original title: NVIDIA has also submitted updated Vera Rubin NVL72 configs for DeepSeek V4.1 Flash. Against GB300’s improved results:

Topics

NVIDIADeployment & engineeringChina AIEvals & benchmarks