Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and Vera Rubin NVL72 (NVIDIA Vera Rubin) on Kimi K3 2.8T. 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
Setting 127 tok/s/user as the target on Kimi K3 2.8T, B300 produces 2488 tok/s/chip ($0.25 per million tokens) and Vera Rubin NVL72 produces 39806 ($0.03). Vera Rubin NVL72 is 902% cheaper per token; Vera Rubin NVL72 delivers 1500% more tok/s/chip.
At 153 tok/s/user interactivity on Kimi K3 2.8T, B300 delivers 2070 tok/s/chip at $0.30 per million tokens; Vera Rubin NVL72 delivers 34857 tok/s/chip at $0.03. Vera Rubin NVL72 is 954% cheaper per token; Vera Rubin NVL72 delivers 1584% more tok/s/chip at this point.
B300 posts 2042 tok/s/chip for $0.31 per million tokens at 178 tok/s/user on Kimi K3 2.8T; Vera Rubin NVL72 posts 30624 tok/s/chip for $0.03. Vera Rubin NVL72 is 839% cheaper per token; Vera Rubin NVL72 delivers 1400% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:2488.2Vera Rubin NVL72:39805.9 | B300:2070.3Vera Rubin NVL72:34856.7 | B300:2042.1Vera Rubin NVL72:30624.1 |
| Cost ($/M tok) | B300:$0.252Vera Rubin NVL72:$0.025 | B300:$0.303Vera Rubin NVL72:$0.029 | B300:$0.307Vera Rubin NVL72:$0.033 |
| tok/s/MW | B300:1309602Vera Rubin NVL72:12062403 | B300:1089641Vera Rubin NVL72:10562643 | B300:1074802Vera Rubin NVL72:9280017 |
| Concurrency | B300:~3Vera Rubin NVL72:~221 | B300:~2Vera Rubin NVL72:~184 | B300:~1Vera Rubin NVL72:~151 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.
