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.
B200: 607 tok/s/GPU, $0.90 per million tokens at 36 tok/s/user on GLM 5/5.1. GB300 NVL72 is unmeasured here.
At 60 tok/s/user on GLM 5/5.1, B200 delivers 349 tok/s/GPU at $1.54 per million tokens; GB300 NVL72 hasn't been benchmarked at this target.
B200 hits 197 tok/s/GPU for $2.77 per million tokens at 84 tok/s/user on GLM 5/5.1. No GB300 NVL72 data at this operating point. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:607.3GB300 NVL72:— | B200:349.5GB300 NVL72:— | B200:196.6GB300 NVL72:— |
| Cost ($/M tok) | B200:$0.899GB300 NVL72:— | B200:$1.542GB300 NVL72:— | B200:$2.773GB300 NVL72:— |
| tok/s/MW | B200:279842GB300 NVL72:— | B200:161045GB300 NVL72:— | B200:90610GB300 NVL72:— |
| Concurrency | B200:~80GB300 NVL72:— | B200:~23GB300 NVL72:— | B200:~10GB300 NVL72:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.