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 8815 tok/s/GPU for $0.06 per million tokens at 83 tok/s/user on DeepSeek R1; MI355X posts 7967 tok/s/GPU for $0.05. MI355X is 22% cheaper per token; B200 delivers 11% more tok/s/GPU.
Throughput at 156 tok/s/user on DeepSeek R1: B200 hits 2070 tok/s/GPU, MI355X hits 2223. Per-million costs land at $0.26 and $0.18 respectively. MI355X is 42% cheaper per token; MI355X delivers 7% more tok/s/GPU.
B200 / MI355X on DeepSeek R1 at 228 tok/s/user: 997 / 604 tok/s/GPU, $0.54 / $0.69 per million tokens. B200 is 27% cheaper per token; B200 delivers 65% more tok/s/GPU. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:8814.6MI355X:7966.7 | B200:2070.2MI355X:2222.7 | B200:996.9MI355X:604.1 |
| Cost ($/M tok) | B200:$0.063MI355X:$0.052 | B200:$0.262MI355X:$0.185 | B200:$0.543MI355X:$0.691 |
| tok/s/MW | B200:4062031MI355X:3006286 | B200:954025MI355X:838750 | B200:459384MI355X:227964 |
| Concurrency | B200:~626MI355X:~283 | B200:~63MI355X:~64 | B200:~3MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.