ICYMI: @​Cognition's engineers ran the first customer-executed benchmark on NVIDIA Vera Rubin NVL72. They measured it against their own NVIDIA GB200 NVL72 base

ICYMI: @​Cognition's engineers ran the first customer-executed benchmark on NVIDIA Vera Rubin NVL72. They measured it against their own NVIDIA GB200 NVL72 baseline. Up to 4.8x the total token throughput for SWE-2 inference. 3.8x the output token throughput for reinforcement learning. Agentic codi…