Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and GB200 NVL72 (NVIDIA Blackwell) on MiniMax M3.1 Flash 428B. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics β 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 β
B200 posts 58986 tok/s/chip for $0.01 per million tokens at 139 tok/s/user on MiniMax M3.1 Flash 428B; GB200 NVL72 posts 46730 tok/s/chip for $0.01. B200 is 36% cheaper per token; B200 delivers 26% more tok/s/chip.
Throughput at 260 tok/s/user on MiniMax M3.1 Flash 428B: B200 hits 26420 tok/s/chip, GB200 NVL72 hits 22841. Per-million costs land at $0.02 and $0.02 respectively. B200 is 24% cheaper per token; B200 delivers 16% more tok/s/chip.
B200 / GB200 NVL72 on MiniMax M3.1 Flash 428B at 381 tok/s/user: 11733 / 12586 tok/s/chip, $0.04 / $0.04 per million tokens. Cost per token is essentially tied; GB200 NVL72 delivers 7% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:58986.4GB200 NVL72:46729.7 | B200:26420.0GB200 NVL72:22841.2 | B200:11732.5GB200 NVL72:12586.4 |
| Cost ($/M tok) | B200:$0.008GB200 NVL72:$0.011 | B200:$0.018GB200 NVL72:$0.023 | B200:$0.041GB200 NVL72:$0.041 |
| tok/s/MW | B200:34494965GB200 NVL72:24989145 | B200:15450308GB200 NVL72:12214560 | B200:6861115GB200 NVL72:6730669 |
| Concurrency | B200:~32GB200 NVL72:~28 | B200:~15GB200 NVL72:~12 | B200:~6GB200 NVL72:~6 |
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.
