DeepSeek V4.1 Flash 552B β B200 vs MI325X
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 52β209 tok/s/user interactivity band, at 91 tok/s/user on DeepSeek V4.1 Flash 552B: B200 runs 357162 tok/s/chip at $0.00/M tokens, MI325X runs 12494 at $0.02/M. B200 is 1718% cheaper per token; B200 delivers 2759% more tok/s/chip.
Setting 130 tok/s/user as the target on DeepSeek V4.1 Flash 552B, B200 produces 316087 tok/s/chip ($0.00 per million tokens) and MI325X produces 6673 ($0.05). B200 is 2912% cheaper per token; B200 delivers 4637% more tok/s/chip.
At 170 tok/s/user interactivity on DeepSeek V4.1 Flash 552B, B200 delivers 202116 tok/s/chip at $0.00 per million tokens; MI325X delivers 4203 tok/s/chip at $0.07. B200 is 2957% cheaper per token; B200 delivers 4709% more tok/s/chip at this point. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:357161.8MI325X:12493.5 | B200:316086.6MI325X:6672.9 | B200:202115.6MI325X:4203.2 |
| Cost ($/M tok) | B200:$0.001MI325X:$0.024 | B200:$0.002MI325X:$0.046 | B200:$0.002MI325X:$0.073 |
| tok/s/MW | B200:208866557MI325X:7392612 | B200:184845952MI325X:3948463 | B200:118196239MI325X:2487116 |
| Concurrency | B200:~256MI325X:~4 | B200:~217MI325X:~1 | B200:~135MI325X:~1 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.