
- Who
- NVIDIA
- What
- reported benchmark results Vera Rubin platform results in MLPerf Training v6.1 and MLPerf Endpoints v1.0
- When
- Quote
In its MLPerf benchmarks debut, with results released today, the NVIDIA Vera Rubin platform delivers leading performance across training, post-training and agentic inference.
What happened
NVIDIA says its Vera Rubin platform swept every MLPerf Training v6.1 benchmark and led across MLPerf Endpoints agentic benchmarks in its debut. On DeepSeek-V3 training, it scaled from 256 to 1,024 GPUs with about 97% efficiency; a provisional Kimi K3 result reports more than 10x the throughput per watt of GB300 NVL72 at a shared minimum interactivity of 50 tokens per second per user. The Vera Rubin Endpoints result is pending MLCommons verification.
Why it matters
Vera Rubin scaled DeepSeek-V3 training from 256 to 1,024 GPUs with about 97% efficiency, while its provisional Kimi K3 result reports over 10x the throughput per watt of GB300 at a shared response speed.
Read next
See the full storyNVIDIA Reports Vera Rubin Debut Results in MLPerf Training and EndpointsThe story so far
NVIDIA said its Vera Rubin platform swept every MLPerf Training v6.1 benchmark and led across MLPerf Endpoints agentic benchmarks in its debut, though its Endpoints results remain pending MLCommons Association verification. On DeepSeek-V3 training, NVIDIA reported that Vera Rubin scaled from 256 to 1,024 GPUs with about 97% efficiency. For MLPerf Endpoints v1.0, a provisional Kimi K3 result showed more than 10x the throughput per watt of GB300 NVL72 at a shared minimum interactivity of 50 tokens per second per user. NVIDIA noted that the provisional Vera Rubin results are subject to change pending peer review.
