Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) on Muse Spark Open 816B. 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
At 123 tok/s/user interactivity on Muse Spark Open 816B, GB200 NVL72 delivers 18284 tok/s/chip at $0.03 per million tokens; GB300 NVL72 delivers 18998 tok/s/chip at $0.03. GB200 NVL72 is 20% cheaper per token; GB300 NVL72 delivers 4% more tok/s/chip at this point.
GB200 NVL72 posts 8872 tok/s/chip for $0.06 per million tokens at 189 tok/s/user on Muse Spark Open 816B; GB300 NVL72 posts 14740 tok/s/chip for $0.04. GB300 NVL72 is 34% cheaper per token; GB300 NVL72 delivers 66% more tok/s/chip.
Throughput at 255 tok/s/user on Muse Spark Open 816B: GB200 NVL72 hits 5701 tok/s/chip, GB300 NVL72 hits 7049. Per-million costs land at $0.09 and $0.09 respectively. Cost per token is essentially tied; GB300 NVL72 delivers 24% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL72:18283.8GB300 NVL72:18998.1 | GB200 NVL72:8872.1GB300 NVL72:14739.8 | GB200 NVL72:5700.9GB300 NVL72:7049.1 |
| Cost ($/M tok) | GB200 NVL72:$0.028GB300 NVL72:$0.034 | GB200 NVL72:$0.058GB300 NVL72:$0.044 | GB200 NVL72:$0.091GB300 NVL72:$0.091 |
| tok/s/MW | GB200 NVL72:9777452GB300 NVL72:8961353 | GB200 NVL72:4744416GB300 NVL72:6952723 | GB200 NVL72:3048613GB300 NVL72:3325057 |
| Concurrency | GB200 NVL72:~13GB300 NVL72:~14 | GB200 NVL72:~7GB300 NVL72:~11 | GB200 NVL72:~3GB300 NVL72:~5 |
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.
