Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) 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
GB300 NVL72 posts 56356 tok/s/chip for $0.01 per million tokens at 158 tok/s/user on MiniMax M3.1 Flash 428B; MI355X posts 22930 tok/s/chip for $0.02. GB300 NVL72 is 60% cheaper per token; GB300 NVL72 delivers 146% more tok/s/chip.
Throughput at 283 tok/s/user on MiniMax M3.1 Flash 428B: GB300 NVL72 hits 20867 tok/s/chip, MI355X hits 13424. Per-million costs land at $0.03 and $0.03 respectively. Cost per token is essentially tied; GB300 NVL72 delivers 55% more tok/s/chip.
GB300 NVL72 / MI355X on MiniMax M3.1 Flash 428B at 407 tok/s/user: 12190 / 7448 tok/s/chip, $0.05 / $0.06 per million tokens. GB300 NVL72 is 6% cheaper per token; GB300 NVL72 delivers 64% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB300 NVL72:56356.4MI355X:22930.4 | GB300 NVL72:20867.4MI355X:13423.6 | GB300 NVL72:12190.0MI355X:7447.7 |
| Cost ($/M tok) | GB300 NVL72:$0.011MI355X:$0.018 | GB300 NVL72:$0.031MI355X:$0.031 | GB300 NVL72:$0.053MI355X:$0.056 |
| tok/s/MW | GB300 NVL72:26583209MI355X:10971506 | GB300 NVL72:9843109MI355X:6422762 | GB300 NVL72:5749991MI355X:3563496 |
| Concurrency | GB300 NVL72:~31MI355X:~14 | GB300 NVL72:~11MI355X:~7 | GB300 NVL72:~6MI355X:~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.
