Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) 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 92 tok/s/user as the target on DeepSeek R1, B200 produces 7189 tok/s/chip ($0.07 per million tokens) and GB300 NVL72 produces 12627 ($0.05). GB300 NVL72 is 32% cheaper per token; GB300 NVL72 delivers 76% more tok/s/chip.
At 161 tok/s/user interactivity on DeepSeek R1, B200 delivers 2027 tok/s/chip at $0.24 per million tokens; GB300 NVL72 delivers 5530 tok/s/chip at $0.12. GB300 NVL72 is 104% cheaper per token; GB300 NVL72 delivers 173% more tok/s/chip at this point.
B200 posts 1271 tok/s/chip for $0.38 per million tokens at 231 tok/s/user on DeepSeek R1; GB300 NVL72 posts 1065 tok/s/chip for $0.60. B200 is 59% cheaper per token; B200 delivers 19% more tok/s/chip. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:7188.7GB300 NVL72:12627.5 | B200:2027.3GB300 NVL72:5529.8 | B200:1270.9GB300 NVL72:1065.2 |
| Cost ($/M tok) | B200:$0.067GB300 NVL72:$0.051 | B200:$0.237GB300 NVL72:$0.116 | B200:$0.378GB300 NVL72:$0.602 |
| tok/s/MW | B200:4203946GB300 NVL72:5956366 | B200:1185562GB300 NVL72:2608393 | B200:743190GB300 NVL72:502459 |
| Concurrency | B200:~369GB300 NVL72:~727 | B200:~58GB300 NVL72:~224 | B200:~29GB300 NVL72:~26 |
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