Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) 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 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
B200 posts 155766 tok/s/chip for $0.00 per million tokens at 210 tok/s/user on DeepSeek V4.1 Flash 552B; MI355X posts 59646 tok/s/chip for $0.01. B200 is 126% cheaper per token; B200 delivers 161% more tok/s/chip.
Throughput at 354 tok/s/user on DeepSeek V4.1 Flash 552B: B200 hits 54317 tok/s/chip, MI355X hits 31817. Per-million costs land at $0.01 and $0.01 respectively. B200 is 48% cheaper per token; B200 delivers 71% more tok/s/chip.
B200 / MI355X on DeepSeek V4.1 Flash 552B at 497 tok/s/user: 18799 / 15332 tok/s/chip, $0.03 / $0.03 per million tokens. B200 is 6% cheaper per token; B200 delivers 23% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:155766.1MI355X:59646.3 | B200:54316.6MI355X:31816.9 | B200:18799.0MI355X:15331.5 |
| Cost ($/M tok) | B200:$0.003MI355X:$0.007 | B200:$0.009MI355X:$0.013 | B200:$0.026MI355X:$0.027 |
| tok/s/MW | B200:91091291MI355X:28538912 | B200:31764104MI355X:15223413 | B200:10993553MI355X:7335665 |
| Concurrency | B200:~93MI355X:~30 | B200:~30MI355X:~8 | B200:~10MI355X:~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.
