DeepSeek R1 — B200 vs GB200 NVL72
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and GB200 NVL72 (NVIDIA Blackwell) on DeepSeek R1. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
Throughput at 75 tok/s/user on DeepSeek R1: B200 hits 2558 tok/s/GPU, GB200 NVL72 hits 5790. Per-million costs land at $0.23 and $0.11 respectively. GB200 NVL72 is 113% cheaper per token; GB200 NVL72 delivers 126% more tok/s/GPU.
B200 / GB200 NVL72 on DeepSeek R1 at 120 tok/s/user: 1110 / 3988 tok/s/GPU, $0.49 / $0.15 per million tokens. GB200 NVL72 is 217% cheaper per token; GB200 NVL72 delivers 259% more tok/s/GPU.
Toward the upper edge of the 31–208 tok/s/user interactivity band, at 164 tok/s/user on DeepSeek R1: B200 runs 751 tok/s/GPU at $0.72/M tokens, GB200 NVL72 runs 818 at $0.81/M. B200 is 12% cheaper per token; GB200 NVL72 delivers 9% more tok/s/GPU. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:2557.7GB200 NVL72:5789.6 | B200:1110.0GB200 NVL72:3987.5 | B200:751.2GB200 NVL72:817.8 |
| Cost ($/M tok) | B200:$0.226GB200 NVL72:$0.106 | B200:$0.488GB200 NVL72:$0.154 | B200:$0.721GB200 NVL72:$0.809 |
| tok/s/MW | B200:1178668GB200 NVL72:2756947 | B200:511524GB200 NVL72:1898817 | B200:346177GB200 NVL72:389416 |
| Concurrency | B200:~160GB200 NVL72:~649 | B200:~119GB200 NVL72:~333 | B200:~21GB200 NVL72:~27 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.