DeepSeek R1 — B200 vs MI325X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI325X (AMD CDNA 3) on DeepSeek R1. 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.
Near the low end of the 15–54 tok/s/user interactivity band, at 25 tok/s/user on DeepSeek R1: B200 runs 5857 tok/s/chip at $0.08/M tokens, MI325X runs 854 at $0.36/M. B200 is 336% cheaper per token; B200 delivers 586% more tok/s/chip.
Setting 35 tok/s/user as the target on DeepSeek R1, B200 produces 5654 tok/s/chip ($0.08 per million tokens) and MI325X produces 677 ($0.45). B200 is 431% cheaper per token; B200 delivers 735% more tok/s/chip.
At 44 tok/s/user interactivity on DeepSeek R1, B200 delivers 5274 tok/s/chip at $0.09 per million tokens; MI325X delivers 457 tok/s/chip at $0.67. B200 is 634% cheaper per token; B200 delivers 1055% more tok/s/chip at this point. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:5856.9MI325X:854.2 | B200:5653.9MI325X:677.5 | B200:5274.0MI325X:456.8 |
| Cost ($/M tok) | B200:$0.082MI325X:$0.358 | B200:$0.085MI325X:$0.451 | B200:$0.091MI325X:$0.669 |
| tok/s/MW | B200:3425112MI325X:505466 | B200:3306371MI325X:400884 | B200:3084218MI325X:270289 |
| Concurrency | B200:~1088MI325X:~33 | B200:~712MI325X:~19 | B200:~389MI325X:~10 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Total Tokens per $1 USD (Owning - Hyperscaler) vs. Interactivity
DeepSeek R1 0528 671B • FP4 • 8K / 1K • Source: SemiAnalysis InferenceX™
TCO $/chip/hr: H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
No data available
Please change the model, sequence, precision, date range or chip selection.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip