GLM 5/5.1 — B200 vs GB200 NVL72
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and GB200 NVL72 (NVIDIA Blackwell) on GLM 5/5.1. 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.
B200 posts 492 tok/s/GPU for $1.10 per million tokens at 38 tok/s/user on GLM 5/5.1; GB200 NVL72 posts 1184 tok/s/GPU for $0.58. GB200 NVL72 is 91% cheaper per token; GB200 NVL72 delivers 141% more tok/s/GPU.
Throughput at 47 tok/s/user on GLM 5/5.1: B200 hits 448 tok/s/GPU, GB200 NVL72 hits 197. Per-million costs land at $1.21 and $3.59 respectively. B200 is 198% cheaper per token; B200 delivers 128% more tok/s/GPU.
B200 / GB200 NVL72 on GLM 5/5.1 at 56 tok/s/user: 419 / 49 tok/s/GPU, $1.30 / $12.1 per million tokens. B200 is 833% cheaper per token; B200 delivers 754% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:492.0GB200 NVL72:1184.3 | B200:448.1GB200 NVL72:196.8 | B200:419.3GB200 NVL72:49.1 |
| Cost ($/M tok) | B200:$1.102GB200 NVL72:$0.577 | B200:$1.205GB200 NVL72:$3.587 | B200:$1.295GB200 NVL72:$12.089 |
| tok/s/MW | B200:226708GB200 NVL72:563960 | B200:206503GB200 NVL72:93728 | B200:193229GB200 NVL72:23391 |
| Concurrency | B200:~458GB200 NVL72:~2084 | B200:~254GB200 NVL72:~284 | B200:~30GB200 NVL72:~27 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.