Nvidia released results on November 16, 2026, showing its Vera Rubin platform making its MLPerf benchmarks debut with leading performance across training and agentic inference. The company also announced the Rubin HPC GPU at the SC26 conference.
MLPerf Benchmarks Debut
In its MLPerf benchmarks debut, the NVIDIA Vera Rubin platform delivers leading performance across training, post-training and agentic inference. NVIDIA swept every MLPerf Training v6.1 benchmark and delivered more than 10x generational gains in throughput per watt for agentic AI in its first MLPerf Endpoints submission.
Rubin HPC GPU
Announced at SC26, NVIDIA Rubin HPC is a new GPU in the NVIDIA Vera Rubin platform designed to accelerate simulation and data processing for science, engineering and analytics workflows. The GPU features more than 50,000 CUDA cores on a single GPU and is expected to be available in 2028.
Key facts and where they come from
- The NVIDIA Vera Rubin platform made its MLPerf benchmarks debut with results released on November 16, 2026.
In its MLPerf benchmarks debut, with results released today, the NVIDIA Vera Rubin platform delivers leading performance across training, post-training and agentic inference.
- Nvidia announced Rubin HPC as a new GPU designed to accelerate simulation and data processing, expected in 2028.
Announced today at SC26, NVIDIA Rubin HPC is a new GPU in the NVIDIA Vera Rubin platform designed to accelerate simulation and data processing for science, engineering and analytics workflows.
- The Rubin HPC GPU features more than 50,000 CUDA cores on a single GPU.
The Rubin HPC GPU features a record number of CUDA cores — more than 50,000 on a single GPU
