--- id: "2026-09-16-mlperf-inference-v6-1" url: "https://postcutoff.com/e/2026-09-16-mlperf-inference-v6-1/" as_of: "2026-11-22T13:32:00+01:00" date: "2026-09-16" date_precision: day category: benchmark importance: 3 confidence: high status: [Confirmed] sources: 7 editor: human editor human_review: null version: "2026-10-07" --- As of: 2026-11-22 13:32 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-09-16-mlperf-inference-v6-1/ # MLPerf Inference v6.1 draws a record 30 submitters and the first Vera Rubin NVL72 results Full title: MLPerf Inference v6.1: record 30 submitters, first peer-reviewed Vera Rubin NVL72 results, new RAG and edge-agentic tests On Sept 16, 2026 MLCommons published MLPerf Inference v6.1 results with a record 30 submitting organizations, two new tests (End-to-End RAG and Edge Agentic Inference) and the first peer-reviewed numbers for NVIDIA's Vera Rubin NVL72 (preview), which NVIDIA says delivers up to 3.7x the throughput of GB300 NVL72 on Qwen3-VL and up to 2.5x on DeepSeek-R1. MLCommons also said the new MLPerf Endpoints suite will replace Inference for the datacenter. ## Key facts - Record 30 submitting organizations, six first-time submitters (Atlas Inference, Crusoe, Orrick, ScitiX, VibeHPC, Naeem Khoshnevis) - New tests: End-to-End RAG (embedding → retriever → re-ranker → LLMs) and Edge Agentic Inference (multi-turn agentic workloads at the edge; NVIDIA ran it with Qwen3.6-27B on Jetson AGX Thor) - Speculative decoding now allowed in the interactive scenario for two benchmarks, plus GPT-OSS - Five new processors/accelerators: AMD Ryzen AI Max+ 395, AMD Instinct MI350P, Intel Arc Pro B70 (available); NVIDIA Rubin and Vera Rubin NVL72 (preview) - Largest system ever submitted to MLPerf Inference: 512 accelerators; plus a heterogeneous two-vendor system and one geographically distributed across the Pacific Ocean - Best per-accelerator server result: VLM test up 2.99x vs v6.0 (six months earlier); DeepSeek-R1 test up 5.7x vs v5.1 (one year earlier) - NVIDIA: Vera Rubin NVL72 up to 3.7x GB300 NVL72 throughput on Qwen3-VL (vLLM + Dynamo) and up to 2.5x on DeepSeek-R1 (TensorRT-LLM); DeepSeek-R1 scaled from 1 to 4 GB300 NVL72 racks (288 GPUs) at 99% scaling efficiency - Over 50% of submitters used MLPerf's new API-centric harness; MLCommons says MLPerf Endpoints 'will replace Inference in our family of benchmarks for the datacenter' ## What happened MLCommons released MLPerf Inference v6.1 on Sept 16, 2026. The round set a participation record (30 organizations) and added two tests aimed at multi-step deployments: an End-to-End RAG pipeline and an Edge Agentic Inference test for multi-turn agentic workloads on single-user edge devices. Speculative decoding became an allowed optimization in some interactive scenarios. NVIDIA submitted preview results for Vera Rubin NVL72 on DeepSeek-R1 and Qwen3-VL, the platform's first peer-reviewed benchmark numbers, claiming up to 3.7x (Qwen3-VL) and 2.5x (DeepSeek-R1) the throughput of GB300 NVL72. Nebius also submitted Vera Rubin NVL72 preview results. AMD (Instinct MI350P, Ryzen AI Max+ 395) and Intel (Arc Pro B70) debuted new chips. NVIDIA additionally cited a 30x gain over GB300 NVL72 in SemiAnalysis's AgentX benchmark in preview testing (not an MLPerf result). MLCommons said its new API-centric harness, used by over half of submitters, is the basis of "MLPerf Endpoints", which will replace MLPerf Inference for datacenter systems. ## Why it matters MLPerf is the main audited cross-vendor inference benchmark. This round gave the first independent check on Vera Rubin's claimed generational gains, and its new tests show the benchmark following the industry from single-shot chat toward RAG pipelines and agents. ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 108 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 78 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 169 days after its cutoff - Grok 4.7 (training cutoff May 2026): 108 days after its cutoff ## Sources 1. [MLCommons: Participation record with new MLPerf Inference v6.1 results](https://mlcommons.org/2026/09/mlperf-inference-v6-1-results/) (mlcommons.org, official) 2. [MLCommons: Where the industry is investing — a look at MLPerf Inference v6.1](https://mlcommons.org/2026/09/chairs-mlperf-inference-v6-1/) (mlcommons.org, official) 3. [NVIDIA: Vera Rubin NVL72 delivers leading performance in MLPerf Inference v6.1 debut](https://blogs.nvidia.com/blog/vera-rubin-nvl72-mlperf-inference/) (blogs.nvidia.com, official) 4. [Nebius: MLPerf Inference v6.1 results on Vera Rubin NVL72](https://nebius.com/blog/posts/mlperf-inference-v6-1-results) (nebius.com, official) 5. [AMD ROCm blog: MLPerf Inference v6.1 submission](https://rocm.blogs.amd.com/artificial-intelligence/mlperf-inf-v6.1/README.html) (rocm.blogs.amd.com, official) 6. [GlobeNewswire: MLCommons press release (Sept 16, 2026)](https://www.globenewswire.com/news-release/2026/09/16/3363348/0/en/mlcommons-sets-participation-record-with-new-mlperf-inference-v6-1-benchmark-results.html) (globenewswire.com, press) 7. [TechTimes: MLPerf v6.1 puts first peer-reviewed numbers on Vera Rubin](https://www.techtimes.com/articles/327658/20260917/mlperf-v61-puts-first-peer-reviewed-numbers-vera-rubin-software-gains-beat-new-hardware.htm) (techtimes.com, press) ## Changes - 2026-10-02 (filed): Created (found via NVIDIA blog while checking lab news). ## Related - 2026-08-26: [NVIDIA posts $96.2B quarter](https://postcutoff.com/e/2026-08-26-nvidia-q2-fy2027-vera-rubin-production/index.md) - 2026-03-16: [NVIDIA GTC 2026: Vera Rubin platform, Groq 3 LPX, Feynman preview and $1T demand outlook](https://postcutoff.com/e/2026-03-16-nvidia-gtc-2026-vera-rubin-feynman/index.md)