GLM 5/5.1 — B200 vs B300
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and B300 (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 40 tok/s/user on GLM 5/5.1: B200 hits 467 tok/s/GPU, B300 hits 844. Per-million costs land at $1.16 and $0.77 respectively. B300 is 50% cheaper per token; B300 delivers 80% more tok/s/GPU.
B200 / B300 on GLM 5/5.1 at 63 tok/s/user: 330 / 560 tok/s/GPU, $1.63 / $1.15 per million tokens. B300 is 41% cheaper per token; B300 delivers 70% more tok/s/GPU.
Toward the upper edge of the 17–108 tok/s/user interactivity band, at 86 tok/s/user on GLM 5/5.1: B200 runs 185 tok/s/GPU at $2.93/M tokens, B300 runs 382 at $1.69/M. B300 is 74% cheaper per token; B300 delivers 106% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:467.4B300:843.5 | B200:329.8B300:560.0 | B200:185.3B300:381.5 |
| Cost ($/M tok) | B200:$1.164B300:$0.774 | B200:$1.627B300:$1.154 | B200:$2.932B300:$1.688 |
| tok/s/MW | B200:215400B300:388714 | B200:151978B300:258066 | B200:85408B300:175812 |
| Concurrency | B200:~499B300:~85 | B200:~21B300:~37 | B200:~9B300:~19 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.