NVIDIA Is Among the First to Submit MLPerf Inference v6.0 Benchmarks With Blackwell Ultra, and It’s Total Domination Over Competitors

NVIDIA was among the first to submit MLPerf Inference v6.0 benchmark results using Blackwell Ultra.

The company reported the highest combined performance versus competitors and large token/sec/GPU gains versus v5.1.

NVIDIA said software optimizations raised DeepSeek-R1 throughput 2.7x without hardware changes.

MLPerf v6.0 added workloads such as DeepSeek-R1, GPT-OSS-120B, and Mixtral 8x7B, widening test coverage.