GLM 5/5.1 · Chip 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 2,532 tok/s/chip for $0.19 per million tokens at 58 tok/s/user on GLM 5/5.1; GB200 NVL72 posts 9,598 tok/s/chip for $0.054. GB200 NVL72 is 72% cheaper per token; GB200 NVL72 delivers 3.8× the tok/s/chip.
Throughput at 86 tok/s/user on GLM 5/5.1: B200 hits 1,796 tok/s/chip, GB200 NVL72 hits 6,589. Costs per million tokens land at $0.27 and $0.078 respectively. GB200 NVL72 is 71% cheaper per token; GB200 NVL72 delivers 3.7× the tok/s/chip.
B200 / GB200 NVL72 on GLM 5/5.1 at 114 tok/s/user: 1,385 / 1,997 tok/s/chip, $0.35 / $0.26 per million tokens. GB200 NVL72 is 25% cheaper per token; GB200 NVL72 delivers 44% more tok/s/chip. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GB200 NVL72 vs B200: full specs & benchmarks across models →
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B2002,532GB200 NVL729,598 | B2001,796GB200 NVL726,589 | B2001,385GB200 NVL721,997 |
| Cost ($/M tok) | B200$0.19GB200 NVL72$0.054 | B200$0.27GB200 NVL72$0.078 | B200$0.35GB200 NVL72$0.26 |
| tok/s/MW | B2001,480,645GB200 NVL725,132,497 | B2001,050,524GB200 NVL723,523,588 | B200809,988GB200 NVL721,067,709 |
| Concurrency | B200~20GB200 NVL72~953 | B200~10GB200 NVL72~664 | B200~5GB200 NVL72~108 |