Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and MI300X (AMD CDNA 3) 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 →
GB200 NVL72 posts 76324 tok/s/chip for $0.01 per million tokens at 61 tok/s/user on DeepSeek V4.1 Flash 552B; MI300X posts 6167 tok/s/chip for $0.04. GB200 NVL72 is 532% cheaper per token; GB200 NVL72 delivers 1138% more tok/s/chip.
Throughput at 104 tok/s/user on DeepSeek V4.1 Flash 552B: GB200 NVL72 hits 52016 tok/s/chip, MI300X hits 4060. Per-million costs land at $0.01 and $0.06 respectively. GB200 NVL72 is 554% cheaper per token; GB200 NVL72 delivers 1181% more tok/s/chip.
GB200 NVL72 / MI300X on DeepSeek V4.1 Flash 552B at 147 tok/s/user: 30273 / 2131 tok/s/chip, $0.02 / $0.12 per million tokens. GB200 NVL72 is 625% cheaper per token; GB200 NVL72 delivers 1320% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL72:76324.2MI300X:6167.0 | GB200 NVL72:52016.3MI300X:4060.2 | GB200 NVL72:30272.7MI300X:2131.3 |
| Cost ($/M tok) | GB200 NVL72:$0.007MI300X:$0.043 | GB200 NVL72:$0.010MI300X:$0.065 | GB200 NVL72:$0.017MI300X:$0.124 |
| tok/s/MW | GB200 NVL72:40815101MI300X:4436697 | GB200 NVL72:27816189MI300X:2921020 | GB200 NVL72:16188620MI300X:1533322 |
| Concurrency | GB200 NVL72:~54MI300X:~10 | GB200 NVL72:~28MI300X:~5 | GB200 NVL72:~17MI300X:~2 |
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.
