Cognition
Role in each timeline
- Nvidia Data Center GPUs: Hopper, Blackwell and Vera Rubin
CoreWeave’s first stated production customer for Vera Rubin NVL72 workloads.
- OpenAI Frontier Models: From GPT-4 to GPT-6 Astra
Applied GPT-6 Astra across its product lineup.
Cognition across every timeline
Every dated entry that names Cognition, from all 2 timelines, newest first.
- Cognition reports Vera Rubin SWE-2 throughput comparison Report
CoreWeave reported that Cognition measured a 4.8 times increase in total token throughput for SWE-2 inference workloads on Vera Rubin NVL72 compared with GB200 NVL72. NVIDIA reported that Cognition observed up to a 4.8 times increase in early tests.
on Nvidia Data Center GPUs: Hopper, Blackwell and Vera Rubin - CoreWeave makes Vera Rubin NVL72 available with Cognition workloads Launch
CoreWeave announced the availability of NVIDIA Vera Rubin NVL72 on its cloud, with Cognition as the first customer anywhere running production workloads on the system.
on Nvidia Data Center GPUs: Hopper, Blackwell and Vera Rubin