Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) on Qwen 3.8 Flash Next 176B-A6B. 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
Throughput at 71 tok/s/user on Qwen 3.8 Flash Next 176B-A6B: B300 hits 81505 tok/s/chip, GB300 NVL72 hits 91644. Per-million costs land at $0.01 and $0.01 respectively. GB300 NVL72 is 10% cheaper per token; GB300 NVL72 delivers 12% more tok/s/chip.
B300 / GB300 NVL72 on Qwen 3.8 Flash Next 176B-A6B at 104 tok/s/user: 69672 / 63790 tok/s/chip, $0.01 / $0.01 per million tokens. B300 is 12% cheaper per token; B300 delivers 9% more tok/s/chip.
Toward the upper edge of the 38β170 tok/s/user interactivity band, at 137 tok/s/user on Qwen 3.8 Flash Next 176B-A6B: B300 runs 52685 tok/s/chip at $0.01/M tokens, GB300 NVL72 runs 44523 at $0.01/M. B300 is 21% cheaper per token; B300 delivers 18% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:81505.3GB300 NVL72:91644.3 | B300:69672.2GB300 NVL72:63789.7 | B300:52685.2GB300 NVL72:44522.7 |
| Cost ($/M tok) | B300:$0.008GB300 NVL72:$0.007 | B300:$0.009GB300 NVL72:$0.010 | B300:$0.012GB300 NVL72:$0.014 |
| tok/s/MW | B300:42897518GB300 NVL72:43228452 | B300:36669601GB300 NVL72:30089471 | B300:27729063GB300 NVL72:21001278 |
| Concurrency | B300:~16GB300 NVL72:~19 | B300:~13GB300 NVL72:~12 | B300:~10GB300 NVL72:~9 |
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.
