GLM 5/5.1 · Chip comparison
GLM 5/5.1 — B300 vs GB200 NVL72
Head-to-head AI inference benchmark comparison of B300 (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.
Near the low end of the 30–147 tok/s/user interactivity band, at 59 tok/s/user on GLM 5/5.1: B300 runs 2,598 tok/s/chip at $0.24 per million tokens, GB200 NVL72 runs 9,553 at $0.054. GB200 NVL72 is 78% cheaper per token; GB200 NVL72 delivers 3.7× the tok/s/chip.
Setting 88 tok/s/user as the target on GLM 5/5.1, B300 produces 1,755 tok/s/chip ($0.36 per million tokens) and GB200 NVL72 produces 6,203 ($0.083). GB200 NVL72 is 77% cheaper per token; GB200 NVL72 delivers 3.5× the tok/s/chip.
At 118 tok/s/user interactivity on GLM 5/5.1, B300 delivers 1,278 tok/s/chip at $0.49 per million tokens; GB200 NVL72 delivers 1,574 tok/s/chip at $0.33. GB200 NVL72 is 33% cheaper per token; GB200 NVL72 delivers 23% more tok/s/chip at this point. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B3002,598GB200 NVL729,553 | B3001,755GB200 NVL726,203 | B3001,278GB200 NVL721,574 |
| Cost ($/M tok) | B300$0.24GB200 NVL72$0.054 | B300$0.36GB200 NVL72$0.083 | B300$0.49GB200 NVL72$0.33 |
| tok/s/MW | B3001,367,336GB200 NVL725,108,387 | B300923,579GB200 NVL723,317,076 | B300672,435GB200 NVL72841,925 |
| Concurrency | B300~20GB200 NVL72~916 | B300~9GB200 NVL72~661 | B300~5GB200 NVL72~75 |