Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI325X (AMD CDNA 3) 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
Near the low end of the 73β215 tok/s/user interactivity band, at 108 tok/s/user on DeepSeek V4.1 Flash 552B: B200 runs 160338 tok/s/chip at $0.00/M tokens, MI325X runs 9974 at $0.03/M. B200 is 922% cheaper per token; B200 delivers 1508% more tok/s/chip.
Setting 144 tok/s/user as the target on DeepSeek V4.1 Flash 552B, B200 produces 126117 tok/s/chip ($0.00 per million tokens) and MI325X produces 6141 ($0.05). B200 is 1206% cheaper per token; B200 delivers 1954% more tok/s/chip.
At 179 tok/s/user interactivity on DeepSeek V4.1 Flash 552B, B200 delivers 73326 tok/s/chip at $0.01 per million tokens; MI325X delivers 4042 tok/s/chip at $0.08. B200 is 1053% cheaper per token; B200 delivers 1714% more tok/s/chip at this point. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:160338.3MI325X:9973.7 | B200:126117.4MI325X:6141.2 | B200:73326.5MI325X:4042.5 |
| Cost ($/M tok) | B200:$0.003MI325X:$0.031 | B200:$0.004MI325X:$0.050 | B200:$0.007MI325X:$0.076 |
| tok/s/MW | B200:93765072MI325X:5901598 | B200:73752883MI325X:3633875 | B200:42880968MI325X:2391989 |
| Concurrency | B200:~74MI325X:~3 | B200:~33MI325X:~4 | B200:~48MI325X:~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.
