Head-to-head AI inference benchmark comparison of B300 (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
B300 posts 21347 tok/s/chip for $0.03 per million tokens at 94 tok/s/user on Muse Spark Open 816B; GB300 NVL72 posts 20760 tok/s/chip for $0.03. B300 is 5% cheaper per token; B300 delivers 3% more tok/s/chip.
Throughput at 174 tok/s/user on Muse Spark Open 816B: B300 hits 14717 tok/s/chip, GB300 NVL72 hits 15908. Per-million costs land at $0.04 and $0.04 respectively. GB300 NVL72 is 6% cheaper per token; GB300 NVL72 delivers 8% more tok/s/chip.
B300 / GB300 NVL72 on Muse Spark Open 816B at 254 tok/s/user: 6068 / 7074 tok/s/chip, $0.10 / $0.09 per million tokens. GB300 NVL72 is 14% cheaper per token; GB300 NVL72 delivers 17% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:21346.8GB300 NVL72:20759.8 | B300:14717.3GB300 NVL72:15907.6 | B300:6067.6GB300 NVL72:7074.2 |
| Cost ($/M tok) | B300:$0.029GB300 NVL72:$0.031 | B300:$0.043GB300 NVL72:$0.040 | B300:$0.103GB300 NVL72:$0.091 |
| tok/s/MW | B300:11235170GB300 NVL72:9792356 | B300:7745925GB300 NVL72:7503605 | B300:3193450GB300 NVL72:3336867 |
| Concurrency | B300:~16GB300 NVL72:~16 | B300:~12GB300 NVL72:~11 | B300:~4GB300 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.
