Head-to-head AI inference benchmark comparison of H100 (NVIDIA Hopper) and MI355X (AMD CDNA 4) 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 →
Near the low end of the 14–275 tok/s/user interactivity band, at 79 tok/s/user on DeepSeek V4.1 Flash 552B: H100 runs 3829 tok/s/chip at $0.08/M tokens, MI355X runs 1517 at $0.27/M. H100 is 223% cheaper per token; H100 delivers 152% more tok/s/chip.
Setting 144 tok/s/user as the target on DeepSeek V4.1 Flash 552B, H100 produces 3829 tok/s/chip ($0.08 per million tokens) and MI355X produces 1517 ($0.27). H100 is 223% cheaper per token; H100 delivers 152% more tok/s/chip.
At 210 tok/s/user interactivity on DeepSeek V4.1 Flash 552B, H100 delivers 3734 tok/s/chip at $0.09 per million tokens; MI355X delivers 1517 tok/s/chip at $0.27. H100 is 215% cheaper per token; H100 delivers 146% more tok/s/chip at this point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H100:3828.8MI355X:1517.5 | H100:3828.8MI355X:1517.5 | H100:3733.7MI355X:1517.5 |
| Cost ($/M tok) | H100:$0.085MI355X:$0.275 | H100:$0.085MI355X:$0.275 | H100:$0.087MI355X:$0.275 |
| tok/s/MW | H100:2794727MI355X:726055 | H100:2794727MI355X:726055 | H100:2725306MI355X:726055 |
| Concurrency | H100:~4MI355X:~1 | H100:~4MI355X:~1 | H100:~4MI355X:~1 |
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.
