Head-to-head AI inference benchmark comparison of GB200 NVL72 (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.
Throughput at 37 tok/s/user on DeepSeek R1: GB200 NVL72 hits 7073 tok/s/chip, MI325X hits 636. Per-million costs land at $0.07 and $0.48 respectively. GB200 NVL72 is 558% cheaper per token; GB200 NVL72 delivers 1012% more tok/s/chip.
GB200 NVL72 / MI325X on DeepSeek R1 at 43 tok/s/user: 6988 / 484 tok/s/chip, $0.07 / $0.63 per million tokens. GB200 NVL72 is 754% cheaper per token; GB200 NVL72 delivers 1345% more tok/s/chip.
Toward the upper edge of the 32–54 tok/s/user interactivity band, at 49 tok/s/user on DeepSeek R1: GB200 NVL72 runs 6529 tok/s/chip at $0.08/M tokens, MI325X runs 336 at $0.91/M. GB200 NVL72 is 1051% cheaper per token; GB200 NVL72 delivers 1845% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL72:7072.6MI325X:636.0 | GB200 NVL72:6988.1MI325X:483.7 | GB200 NVL72:6529.4MI325X:335.6 |
| Cost ($/M tok) | GB200 NVL72:$0.073MI325X:$0.480 | GB200 NVL72:$0.074MI325X:$0.632 | GB200 NVL72:$0.079MI325X:$0.910 |
| tok/s/MW | GB200 NVL72:3782124MI325X:376349 | GB200 NVL72:3736945MI325X:286241 | GB200 NVL72:3491637MI325X:198588 |
| Concurrency | GB200 NVL72:~2484MI325X:~17 | GB200 NVL72:~4883MI325X:~11 | GB200 NVL72:~1994MI325X:~7 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
TCO $/chip/hr: VR200: 3.61H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68Jalapeño (Teacup): 1.47
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.
Matching measurements exist, but their chip series are hidden.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip
DeepSeek R1 0528 671B 8K / 1K Total Tokens per $1 TCO vs. Interactivity