Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and Vera Rubin NVL72 (NVIDIA Vera Rubin) on MiniMax M3 428B. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics β same interactions as the main inference chart.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX β
GB200 NVL72 posts 18834 tok/s/chip for $0.03 per million tokens at 184 tok/s/user on MiniMax M3 428B; Vera Rubin NVL72 posts 145238 tok/s/chip for $0.01. Vera Rubin NVL72 is 297% cheaper per token; Vera Rubin NVL72 delivers 671% more tok/s/chip.
Throughput at 267 tok/s/user on MiniMax M3 428B: GB200 NVL72 hits 12749 tok/s/chip, Vera Rubin NVL72 hits 101030. Per-million costs land at $0.04 and $0.01 respectively. Vera Rubin NVL72 is 308% cheaper per token; Vera Rubin NVL72 delivers 692% more tok/s/chip.
GB200 NVL72 / Vera Rubin NVL72 on MiniMax M3 428B at 350 tok/s/user: 7064 / 61148 tok/s/chip, $0.07 / $0.02 per million tokens. Vera Rubin NVL72 is 346% cheaper per token; Vera Rubin NVL72 delivers 766% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL72:18834.3Vera Rubin NVL72:145237.9 | GB200 NVL72:12749.3Vera Rubin NVL72:101029.6 | GB200 NVL72:7063.9Vera Rubin NVL72:61148.1 |
| Cost ($/M tok) | GB200 NVL72:$0.027Vera Rubin NVL72:$0.007 | GB200 NVL72:$0.041Vera Rubin NVL72:$0.010 | GB200 NVL72:$0.073Vera Rubin NVL72:$0.016 |
| tok/s/MW | GB200 NVL72:10071833Vera Rubin NVL72:44011476 | GB200 NVL72:6817810Vera Rubin NVL72:30615033 | GB200 NVL72:3777480Vera Rubin NVL72:18529728 |
| Concurrency | GB200 NVL72:~12Vera Rubin NVL72:~43 | GB200 NVL72:~6Vera Rubin NVL72:~29 | GB200 NVL72:~1Vera Rubin NVL72:~18 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
TCO $/chip/hr:
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.
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.
Shift+Scroll to zoom β’ Drag to pan β’ Double-click to reset β’ Click a point to pin tooltip
MiniMax M3 428B 8K / 1K Total Tokens per $1 TCO vs. Median Interactivity