Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and MI300X (AMD CDNA 3) on MiniMax M2.5/M2.7. 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.
Near the low end of the 31–84 tok/s/user interactivity band, at 44 tok/s/user on MiniMax M2.5/M2.7: GB200 NVL72 runs 9645 tok/s/chip at $0.05/M tokens, MI300X runs 1469 at $0.18/M. GB200 NVL72 is 235% cheaper per token; GB200 NVL72 delivers 557% more tok/s/chip.
Setting 57 tok/s/user as the target on MiniMax M2.5/M2.7, GB200 NVL72 produces 7195 tok/s/chip ($0.07 per million tokens) and MI300X produces 1256 ($0.21). GB200 NVL72 is 193% cheaper per token; GB200 NVL72 delivers 473% more tok/s/chip.
At 71 tok/s/user interactivity on MiniMax M2.5/M2.7, GB200 NVL72 delivers 4540 tok/s/chip at $0.11 per million tokens; MI300X delivers 990 tok/s/chip at $0.27. GB200 NVL72 is 134% cheaper per token; GB200 NVL72 delivers 359% more tok/s/chip at this point. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL72:9645.3MI300X:1469.1 | GB200 NVL72:7194.8MI300X:1255.9 | GB200 NVL72:4540.3MI300X:989.6 |
| Cost ($/M tok) | GB200 NVL72:$0.054MI300X:$0.180 | GB200 NVL72:$0.072MI300X:$0.210 | GB200 NVL72:$0.114MI300X:$0.267 |
| tok/s/MW | GB200 NVL72:5157936MI300X:1056894 | GB200 NVL72:3847513MI300X:903492 | GB200 NVL72:2427969MI300X:711944 |
| Concurrency | GB200 NVL72:~180MI300X:~8 | GB200 NVL72:~88MI300X:~5 | GB200 NVL72:~47MI300X:~4 |
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
