GLM 5/5.1 · GPU comparison

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 2532 tok/s/GPU for $0.21 per million tokens at 58 tok/s/user on GLM 5/5.1; GB200 NVL72 posts 9598 tok/s/GPU for $0.06. GB200 NVL72 is 234% cheaper per token; GB200 NVL72 delivers 279% more tok/s/GPU.

Throughput at 86 tok/s/user on GLM 5/5.1: B200 hits 1796 tok/s/GPU, GB200 NVL72 hits 6589. Per-million costs land at $0.30 and $0.09 respectively. GB200 NVL72 is 227% cheaper per token; GB200 NVL72 delivers 267% more tok/s/GPU.

B200 / GB200 NVL72 on GLM 5/5.1 at 114 tok/s/user: 1385 / 1997 tok/s/GPU, $0.39 / $0.31 per million tokens. GB200 NVL72 is 27% cheaper per token; GB200 NVL72 delivers 44% more tok/s/GPU. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)

View performance-per-dollar view →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Throughput (tok/s/gpu)
B200:2531.9GB200 NVL72:9597.8
B200:1796.4GB200 NVL72:6589.1
B200:1385.1GB200 NVL72:1996.6
Cost ($/M tok)
B200:$0.214GB200 NVL72:$0.064
B200:$0.303GB200 NVL72:$0.093
B200:$0.393GB200 NVL72:$0.309
tok/s/MW
B200:1480645GB200 NVL72:5132497
B200:1050524GB200 NVL72:3523588
B200:809988GB200 NVL72:1067709
Concurrency
B200:~20GB200 NVL72:~953
B200:~10GB200 NVL72:~664
B200:~5GB200 NVL72:~108

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.

Vendor:
Aggregation:
Spec Decoding: