DeepSeek-R1-671B per-GPU throughput improvement
Company: CoreWeave
The claim, verbatim
CoreWeave increased per-GPU server throughput by 19.8% on NVIDIA GB200 NVL72 from MLPerf v6.0 to v6.1
Source (primary)
MLPerf® Inference v6.1 Results: CoreWeave Leads Providers - CoreWeave (-, news_article)
View cached copy (2026-09-19)Live source ↗
Quote: “derived per-GPU Server throughput increased by 19.8%”
How we checked this
Checked on September 24, 2026. The cited source supports every part of this claim.
The post states that per-GPU server throughput on GB200 NVL72 rose 19.8% from v6.0 to v6.1. It notes this compares a 64-GPU v6.0 submission with a 72-GPU v6.1 submission, and that per-GPU figures are derived and not verified by MLCommons.
Confirmed in the source:
- CoreWeave's derived per-GPU server throughput on DeepSeek-R1-671B increased by 19.8%
- The comparison is on NVIDIA GB200 NVL72
- The comparison is between the MLPerf Inference v6.0 and v6.1 submissions
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: “derived per-GPU Server throughput increased by 19.8%”