GLM 5/5.1 · GPU comparison

GLM 5/5.1 — B200 vs GB300 NVL72

Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and GB300 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.

Throughput at 43 tok/s/user on GLM 5/5.1: B200 hits 460 tok/s/GPU, GB300 NVL72 hits 2618. Per-million costs land at $1.18 and $0.41 respectively. GB300 NVL72 is 188% cheaper per token; GB300 NVL72 delivers 470% more tok/s/GPU.

B200 / GB300 NVL72 on GLM 5/5.1 at 67 tok/s/user: 356 / 479 tok/s/GPU, $1.53 / $1.49 per million tokens. GB300 NVL72 is 3% cheaper per token; GB300 NVL72 delivers 35% more tok/s/GPU.

Toward the upper edge of the 19–115 tok/s/user interactivity band, at 91 tok/s/user on GLM 5/5.1: B200 runs 237 tok/s/GPU at $2.30/M tokens, GB300 NVL72 runs 171 at $4.14/M. B200 is 80% cheaper per token; B200 delivers 39% 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.)

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)
B200:459.6GB300 NVL72:2618.4
B200:356.0GB300 NVL72:479.0
B200:237.4GB300 NVL72:171.4
Cost ($/M tok)
B200:$1.180GB300 NVL72:$0.410
B200:$1.532GB300 NVL72:$1.489
B200:$2.299GB300 NVL72:$4.142
tok/s/MW
B200:211792GB300 NVL72:1246843
B200:164046GB300 NVL72:228110
B200:109407GB300 NVL72:81616
Concurrency
B200:~424GB300 NVL72:~3177
B200:~21GB300 NVL72:~307
B200:~11GB300 NVL72:~79

Inference Performance

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

Vendor:
Aggregation:
Spec Decoding: