GLM 5/5.1 · Chip comparison

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 9,135 tok/s/chip, GB300 NVL72 hits 10,192. Costs per million tokens land at $0.057 and $0.063 respectively. GB200 NVL72 is 10% cheaper per token; GB300 NVL72 delivers 12% more tok/s/chip.

GB200 NVL72 / GB300 NVL72 on GLM 5/5.1 at 104 tok/s/user: 3,619 / 4,394 tok/s/chip, $0.14 / $0.15 per million tokens. GB200 NVL72 is 2% cheaper per token; GB300 NVL72 delivers 21% more tok/s/chip.

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/chip at $0.82 per million tokens, GB300 NVL72 runs 837 at $0.77. GB300 NVL72 is 7% cheaper per token; GB300 NVL72 delivers 33% 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.)

View performance per dollar →

GB300 NVL72 vs GB200 NVL72: 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)
GB200 NVL729,135GB300 NVL7210,192
GB200 NVL723,619GB300 NVL724,394
GB200 NVL72630GB300 NVL72837
Cost ($/M tok)
GB200 NVL72$0.057GB300 NVL72$0.063
GB200 NVL72$0.14GB300 NVL72$0.15
GB200 NVL72$0.82GB300 NVL72$0.77
tok/s/MW
GB200 NVL724,885,238GB300 NVL724,807,740
GB200 NVL721,935,265GB300 NVL722,072,464
GB200 NVL72336,816GB300 NVL72394,893
Concurrency
GB200 NVL72~698GB300 NVL72~749
GB200 NVL72~231GB300 NVL72~276
GB200 NVL72~62GB300 NVL72~23