DeepSeek R1 — B200 vs H100
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and H100 (NVIDIA Hopper) on DeepSeek R1. 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 / H100 on DeepSeek R1 at 42 tok/s/user: 4792 / 266 tok/s/GPU, $0.11 / $1.36 per million tokens. B200 is 1109% cheaper per token; B200 delivers 1699% more tok/s/GPU.
Around the middle of the 14–128 tok/s/user interactivity band, at 71 tok/s/user on DeepSeek R1: B200 runs 1020 tok/s/GPU at $0.54/M tokens, H100 runs 73 at $4.86/M. B200 is 794% cheaper per token; B200 delivers 1290% more tok/s/GPU.
Setting 100 tok/s/user as the target on DeepSeek R1, B200 produces 497 tok/s/GPU ($1.09 per million tokens) and H100 produces 23 ($15.7). B200 is 1342% cheaper per token; B200 delivers 2039% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:4791.6H100:266.3 | B200:1020.2H100:73.4 | B200:497.5H100:23.3 |
| Cost ($/M tok) | B200:$0.113H100:$1.365 | B200:$0.544H100:$4.864 | B200:$1.088H100:$15.692 |
| tok/s/MW | B200:2208100H100:153957 | B200:470144H100:42434 | B200:229243H100:13443 |
| Concurrency | B200:~1577H100:~558 | B200:~59H100:~52 | B200:~139H100:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.