Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and GB200 NVL72 (NVIDIA Blackwell) on DeepSeek V4.1 Flash 552B. 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Throughput at 112 tok/s/user on DeepSeek V4.1 Flash 552B: B200 hits 59674 tok/s/chip, GB200 NVL72 hits 54384. Per-million costs land at $0.01 and $0.01 respectively. B200 is 18% cheaper per token; B200 delivers 10% more tok/s/chip.
B200 / GB200 NVL72 on DeepSeek V4.1 Flash 552B at 217 tok/s/user: 33922 / 29616 tok/s/chip, $0.01 / $0.02 per million tokens. B200 is 23% cheaper per token; B200 delivers 15% more tok/s/chip.
Toward the upper edge of the 8–425 tok/s/user interactivity band, at 321 tok/s/user on DeepSeek V4.1 Flash 552B: B200 runs 17513 tok/s/chip at $0.03/M tokens, GB200 NVL72 runs 15364 at $0.03/M. B200 is 23% cheaper per token; B200 delivers 14% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:59674.5GB200 NVL72:54383.9 | B200:33921.5GB200 NVL72:29616.3 | B200:17512.9GB200 NVL72:15363.6 |
| Cost ($/M tok) | B200:$0.008GB200 NVL72:$0.010 | B200:$0.014GB200 NVL72:$0.017 | B200:$0.027GB200 NVL72:$0.034 |
| tok/s/MW | B200:34897350GB200 NVL72:29082292 | B200:19837152GB200 NVL72:15837580 | B200:10241441GB200 NVL72:8215833 |
| Concurrency | B200:~50GB200 NVL72:~16 | B200:~9GB200 NVL72:~8 | B200:~5GB200 NVL72:~3 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.
