Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) 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
Throughput at 98 tok/s/user on MiniMax M3.1 Flash 428B: H200 hits 9345 tok/s/chip, MI355X hits 49340. Per-million costs land at $0.04 and $0.01 respectively. MI355X is 329% cheaper per token; MI355X delivers 428% more tok/s/chip.
H200 / MI355X on MiniMax M3.1 Flash 428B at 164 tok/s/user: 6603 / 22145 tok/s/chip, $0.05 / $0.02 per million tokens. MI355X is 173% cheaper per token; MI355X delivers 235% more tok/s/chip.
Toward the upper edge of the 34β294 tok/s/user interactivity band, at 229 tok/s/user on MiniMax M3.1 Flash 428B: H200 runs 3991 tok/s/chip at $0.08/M tokens, MI355X runs 16901 at $0.02/M. MI355X is 244% cheaper per token; MI355X delivers 323% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H200:9344.9MI355X:49340.3 | H200:6603.1MI355X:22144.8 | H200:3991.4MI355X:16901.4 |
| Cost ($/M tok) | H200:$0.036MI355X:$0.008 | H200:$0.051MI355X:$0.019 | H200:$0.085MI355X:$0.025 |
| tok/s/MW | H200:6821067MI355X:23607795 | H200:4819770MI355X:10595597 | H200:2913406MI355X:8086800 |
| Concurrency | H200:~14MI355X:~32 | H200:~8MI355X:~13 | H200:~5MI355X:~9 |
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.
