DeepSeek R1 — B200 vs MI355X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) 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.
B200 posts 7986 tok/s/chip for $0.06 per million tokens at 87 tok/s/user on DeepSeek R1; MI355X posts 7916 tok/s/chip for $0.05. MI355X is 14% cheaper per token; throughput per chip is essentially tied.
Throughput at 158 tok/s/user on DeepSeek R1: B200 hits 2053 tok/s/chip, MI355X hits 2139. Per-million costs land at $0.23 and $0.19 respectively. MI355X is 20% cheaper per token; MI355X delivers 4% more tok/s/chip.
B200 / MI355X on DeepSeek R1 at 229 tok/s/user: 1276 / 596 tok/s/chip, $0.38 / $0.70 per million tokens. B200 is 86% cheaper per token; B200 delivers 114% more tok/s/chip. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:7986.1MI355X:7916.5 | B200:2052.6MI355X:2139.3 | B200:1275.7MI355X:596.2 |
| Cost ($/M tok) | B200:$0.060MI355X:$0.053 | B200:$0.234MI355X:$0.195 | B200:$0.377MI355X:$0.699 |
| tok/s/MW | B200:4670252MI355X:3787787 | B200:1200340MI355X:1023603 | B200:745995MI355X:285244 |
| Concurrency | B200:~497MI355X:~254 | B200:~62MI355X:~64 | B200:~31MI355X:~8 |
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