Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on GLM 5.3 744B. 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 14087 tok/s/chip for $0.04 per million tokens at 122 tok/s/user on GLM 5.3 744B; MI355X posts 6643 tok/s/chip for $0.06. GB200 NVL72 is 71% cheaper per token; GB200 NVL72 delivers 112% more tok/s/chip.
Throughput at 154 tok/s/user on GLM 5.3 744B: GB200 NVL72 hits 11570 tok/s/chip, MI355X hits 3745. Per-million costs land at $0.04 and $0.11 respectively. GB200 NVL72 is 149% cheaper per token; GB200 NVL72 delivers 209% more tok/s/chip.
GB200 NVL72 / MI355X on GLM 5.3 744B at 185 tok/s/user: 9506 / 2719 tok/s/chip, $0.05 / $0.15 per million tokens. GB200 NVL72 is 182% cheaper per token; GB200 NVL72 delivers 250% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL72:14086.6MI355X:6642.9 | GB200 NVL72:11570.0MI355X:3744.6 | GB200 NVL72:9505.8MI355X:2718.7 |
| Cost ($/M tok) | GB200 NVL72:$0.037MI355X:$0.063 | GB200 NVL72:$0.045MI355X:$0.111 | GB200 NVL72:$0.054MI355X:$0.153 |
| tok/s/MW | GB200 NVL72:7532919MI355X:3178399 | GB200 NVL72:6187180MI355X:1791652 | GB200 NVL72:5083324MI355X:1300826 |
| Concurrency | GB200 NVL72:~86MI355X:~6 | GB200 NVL72:~55MI355X:~2 | GB200 NVL72:~46MI355X:~4 |
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.
