CoreWeave Achieves New Record-Breaking AI Inferencing Benchmark with NVIDIA GB200 Grace Blackwell Superchips

CoreWeave Achieves New Record-Breaking AI Inferencing Benchmark with NVIDIA GB200 Grace Blackwell Superchips

Announcement

Announcement

Webinar

Announcement

Podcast

Announcement

GTC 2026

Announcement

CoreWeave brings up the industry’s first NVIDIA Vera Rubin NVL72 deployment.

Read more

Products

Data and storage

Infrastructure control

Runtime acceleration

Model and agent development

Mission control

Solutions

Pricing

Resources

About us

Contact us Login

Contact us Login

Clear

CoreWeave is the first cloud service provider to submit MLPerf Inference v5.0 results for NVIDIA GB200 Superchips LIVINGSTON, N.J., April 2, 2025 /PRNewswire/ -- CoreWeave, the AI Hyperscaler™, today announced its MLPerf v5.0 results, setting a new industry benchmark in AI inference with NVIDIA GB200 Grace Blackwell Superchips. Using a CoreWeave instance with NVIDIA GB200, featuring two NVIDIA Grace CPUs and four NVIDIA Blackwell GPUs, CoreWeave delivered 800 tokens per second (TPS) on the Llama 3.1 405B model 1 —one of the largest open-source models. "CoreWeave is committed to delivering cutting-edge infrastructure optimized for large-model inference through our purpose-built cloud platform," said Peter Salanki, Chief Technology Officer at CoreWeave. "These benchmark MLPerf results reinforce CoreWeave's position as a preferred cloud provider for leading AI labs and enterprises." CoreWeave also submitted new results for NVIDIA H200 GPU instances. It achieved 33,000 TPS on the Llama 2 70B model, representing a 40 percent improvement in throughput over NVIDIA H100 instances. 2 These results further demonstrate CoreWeave as an industry-leading cloud infrastructure services provider. This year, the company became the first to offer general availability of NVIDIA GB200 NVL72-based instances. Last year, the company was among the first to offer NVIDIA H100 and H200 GPUs, and it was one of the first to demo NVIDIA GB200 NVL72. MLPerf Inference is an industry-standard suite for measuring machine learning performance across realistic deployment scenarios. How quickly systems can process inputs and produce results using a trained model has a direct impact on user experience.

About CoreWeave ‍ ‍ CoreWeave is The Essential Cloud for AI™. Built for pioneers by pioneers, CoreWeave delivers a platform of technology, tools, and teams that enables innovators to move at the pace of innovation, building and scaling AI with confidence. Trusted by leading AI labs, startups, and global enterprises, CoreWeave serves as a force multiplier by combining superior infrastructure performance with deep technical expertise to accelerate breakthroughs. Established in 2017, CoreWeave completed its public listing on Nasdaq (CRWV) in March 2025. Learn more at www.coreweave.com . ‍

Media Contact: Gurion Kastenberg, press@coreweave.com ‍ 1 Verified MLPerf® score of v5.1 Inference Closed Llama 3.1 405B offline. Retrieved from https://mlcommons.org/benchmarks/inference , 2 April 2025, entry 5.0-0076. The MLPerf name and logo are registered and unregistered trademarks of MLCommons Association in the United States and other countries. All rights reserved. Unauthorized use strictly prohibited. See www.mlcommons.org for more information. 2 Verified MLPerf® score of v5.1 Inference Closed Llama 2 70B server. Retrieved from https://mlcommons.org/benchmarks/inference , 2 April 2025, entry 5.0-0077. The MLPerf name and logo are registered and unregistered trademarks of MLCommons Association in the United States and other countries. All rights reserved. Unauthorized use strictly prohibited. See www.mlcommons.org for more information. SOURCE CoreWeave To see the release on PR Newswire, please click here. ‍

Share this article: Copied

Media Contacts CoreWeave Media press@coreweave.com

More press releases

CoreWeave Completes Industry-First Bring-Up and Validation of NVIDIA Vera Rubin NVL72

4 min read

CoreWeave Closes the Training-to-Inference Gap for Autonomous Agent Improvement CoreWeave launches unified agentic AI capabilities that connect training, inference, observability, and RL so AI agents continuously learn and improve in production. 3 min read

CoreWeave Sandboxes Launches to Accelerate Reinforcement Learning, Agent Tool Use, and Model Evaluation Secure, isolated environments for running AI tool use and evaluation at scale 4 min read

CoreWeave Achieves #1 Ranking for Inference Speed and Price-Performance for Moonshot AI’s Kimi K2.6 Model in Independent Benchmark Full stack optimization across memory architecture, runtime, and interconnect translates into the speed and economics enterprises need to run open-source AI in production 2 min read

CoreWeave SUNK Expands Capabilities to Bring AI Workloads Online Faster – Anywhere SUNK Self-Service and SUNK Anywhere Advance How AI Workloads are Set Up and Run Across Cloud Environments 4 min read

CEO Michael Intrator's 2025 Letter to Shareholders CoreWeave publishes its first annual shareholder letter detailing AI's move from possibility to prerequisite, the company's financial discipline and technology advantage, and what's ahead.

min read

Jane Street Signs $6 Billion AI Cloud Agreement with CoreWeave Jane Street will invest $6B in CoreWeave’s AI cloud and $1B in equity, expanding their partnership to power large-scale machine learning and trading. 2 min read

CoreWeave Announces Multi-Year Agreement With Anthropic CoreWeave announces a multi-year agreement with Anthropic to support the development and deployment of Anthropic's Claude family of AI models. 2 min read

CoreWeave and Meta Announce $21 Billion Expanded AI Infrastructure Agreement Meta to leverage CoreWeave’s AI cloud platform to scale inference workloads, underscoring the surging demand for large-scale AI compute 1 min read

CoreWeave Delivers Leading Inference Performance in MLPerf® Benchmark CoreWeave leads MLPerf v6.0 inference benchmarks, doubling performance and showcasing how its optimized AI cloud delivers real-world, production-ready results at scale. 3 min read

Contact us Login

Products GPU Compute CPU Compute Storage Services Networking Services Managed Services Bare Metal Servers Platform Fleet LifeCycle Controller

Node LifeCycle Controller Tensorizer Observability

Solutions AI Model Training AI Inference VFX & Rendering Mission Control

AI Infrastructure

Why CoreWeave

Resources Customer Stories Documentation Status Pricing Resource Center Events & Webinars

About…