GPT-OSS-120B on GB200 NVL72 offline
Company: CoreWeave
The claim, verbatim
CoreWeave's NVIDIA GB200 NVL72 achieved 911,566 tokens per second in offline scenario for GPT-OSS-120B
Source (primary)
MLPerf® Inference v6.1 Results: CoreWeave Leads Providers - CoreWeave (-, news_article)
View cached copy (2026-09-19)Live source ↗
Quote: “911,566 tokens per second in offline scenarios”
How we checked this
Checked on September 24, 2026. The cited source supports every part of this claim.
The post reports 911,566 tokens per second in the offline scenario for CoreWeave's GB200 NVL72 on GPT-OSS-120B.
Confirmed in the source:
- CoreWeave's NVIDIA GB200 NVL72 reached 911,566 tokens per second in the offline scenario on GPT-OSS-120B
What we did: Read our cached copy of the publisher (https://www.coreweave.com/blog/coreweave-leads-cloud-providers-in-mlperf-r-inference-v6-1-performance-with-nvidia-blackwell-ultra) in full (14,189 characters, retrieved September 19, 2026) and checked each assertion in the claim against it.
Additional evidence
confirms MLPerf® Inference v6.1 Results: CoreWeave Leads Providers - CoreWeave
Quote: “911,566 tokens per second in offline scenarios”