Vera Rubin Inference Results Leave Nvidia’s 75% Training Claim Untested

Oct. 15 AA-AgentPerf results put Vera Rubin NVL72 at 5.7 times GB300’s total throughput per megawatt at a specific speed, while leaving Nvidia’s separate training estimate untested. The finding measures inference — generating outputs from a trained model — rather than a completed training run. The benchmark exercised coding-agent tasks with DeepSeek V4 Pro. At the selected operating point, Vera Rubin produced about 190 output tokens per second for each user. GB300 rack configurations did not reach that rate, so the comparison used a four-GPU GB300 setup. The 5.7-times result reflects that configuration and speed, rather than a full-rack comparison.

Source: TokenPost