GLM 5/5.1 — GB200 NVL72 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of GB200 NVL72 (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 67 tok/s/user on GLM 5/5.1: GB200 NVL72 hits 9135 tok/s/GPU, GB300 NVL72 hits 10192. Per-million costs land at $0.07 and $0.07 respectively. GB200 NVL72 is 7% cheaper per token; GB300 NVL72 delivers 12% more tok/s/GPU.
GB200 NVL72 / GB300 NVL72 on GLM 5/5.1 at 104 tok/s/user: 3619 / 4394 tok/s/GPU, $0.17 / $0.17 per million tokens. Cost per token is essentially tied; GB300 NVL72 delivers 21% more tok/s/GPU.
Toward the upper edge of the 30–177 tok/s/user interactivity band, at 141 tok/s/user on GLM 5/5.1: GB200 NVL72 runs 630 tok/s/GPU at $0.98/M tokens, GB300 NVL72 runs 837 at $0.84/M. GB300 NVL72 is 16% cheaper per token; GB300 NVL72 delivers 33% more tok/s/GPU. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB200 NVL72:9135.4GB300 NVL72:10192.4 | GB200 NVL72:3618.9GB300 NVL72:4393.6 | GB200 NVL72:629.8GB300 NVL72:837.2 |
| Cost ($/M tok) | GB200 NVL72:$0.068GB300 NVL72:$0.072 | GB200 NVL72:$0.168GB300 NVL72:$0.167 | GB200 NVL72:$0.976GB300 NVL72:$0.839 |
| tok/s/MW | GB200 NVL72:4885238GB300 NVL72:4807740 | GB200 NVL72:1935265GB300 NVL72:2072464 | GB200 NVL72:336816GB300 NVL72:394893 |
| Concurrency | GB200 NVL72:~698GB300 NVL72:~749 | GB200 NVL72:~231GB300 NVL72:~276 | GB200 NVL72:~62GB300 NVL72:~23 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.