DeepSeek R1 — B200 vs MI300X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI300X (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.
Setting 23 tok/s/user as the target on DeepSeek R1, B200 produces 5857 tok/s/GPU ($0.09 per million tokens) and MI300X produces 725 ($0.43). B200 is 364% cheaper per token; B200 delivers 708% more tok/s/GPU.
At 32 tok/s/user interactivity on DeepSeek R1, B200 delivers 5515 tok/s/GPU at $0.10 per million tokens; MI300X delivers 601 tok/s/GPU at $0.51. B200 is 415% cheaper per token; B200 delivers 817% more tok/s/GPU at this point.
B200 posts 5220 tok/s/GPU for $0.10 per million tokens at 42 tok/s/user on DeepSeek R1; MI300X posts 406 tok/s/GPU for $0.75. B200 is 615% cheaper per token; B200 delivers 1185% more tok/s/GPU. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:5856.9MI300X:725.2 | B200:5515.0MI300X:601.1 | B200:5219.6MI300X:406.3 |
| Cost ($/M tok) | B200:$0.092MI300X:$0.429 | B200:$0.099MI300X:$0.510 | B200:$0.105MI300X:$0.750 |
| tok/s/MW | B200:2699051MI300X:405137 | B200:2541453MI300X:335808 | B200:2405368MI300X:226972 |
| Concurrency | B200:~1088MI300X:~30 | B200:~1005MI300X:~18 | B200:~557MI300X:~10 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.