GLM 5/5.1 · Chip comparison

GLM 5/5.1 — GB300 NVL72 vs H200

Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and H200 (NVIDIA Hopper) 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.

GB300 NVL72 hits 10,192 tok/s/chip for $0.063 per million tokens at 67 tok/s/user on GLM 5/5.1. No H200 data at this operating point.

GB300 NVL72: 4,238 tok/s/chip, $0.15 per million tokens at 105 tok/s/user on GLM 5/5.1. H200 is unmeasured here.

At 143 tok/s/user on GLM 5/5.1, GB300 NVL72 delivers 802 tok/s/chip at $0.80 per million tokens; H200 hasn't been benchmarked at this target. (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 →

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)
GB300 NVL7210,192H200—
GB300 NVL724,238H200—
GB300 NVL72802H200—
Cost ($/M tok)
GB300 NVL72$0.063H200—
GB300 NVL72$0.15H200—
GB300 NVL72$0.80H200—
tok/s/MW
GB300 NVL724,807,740H200—
GB300 NVL721,999,045H200—
GB300 NVL72378,127H200—
Concurrency
GB300 NVL72~749H200—
GB300 NVL72~263H200—
GB300 NVL72~22H200—