Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) on MiniMax M3.1 Flash 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
B300 / GB300 NVL72 on MiniMax M3.1 Flash 428B at 145 tok/s/user: 61216 / 83337 tok/s/chip, $0.01 / $0.01 per million tokens. GB300 NVL72 is 33% cheaper per token; GB300 NVL72 delivers 36% more tok/s/chip.
Around the middle of the 10β549 tok/s/user interactivity band, at 280 tok/s/user on MiniMax M3.1 Flash 428B: B300 runs 22779 tok/s/chip at $0.03/M tokens, GB300 NVL72 runs 39560 at $0.02/M. GB300 NVL72 is 70% cheaper per token; GB300 NVL72 delivers 74% more tok/s/chip.
Setting 415 tok/s/user as the target on MiniMax M3.1 Flash 428B, B300 produces 9485 tok/s/chip ($0.07 per million tokens) and GB300 NVL72 produces 16791 ($0.04). GB300 NVL72 is 73% cheaper per token; GB300 NVL72 delivers 77% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:61215.8GB300 NVL72:83337.4 | B300:22778.5GB300 NVL72:39559.5 | B300:9484.9GB300 NVL72:16791.3 |
| Cost ($/M tok) | B300:$0.010GB300 NVL72:$0.008 | B300:$0.028GB300 NVL72:$0.016 | B300:$0.066GB300 NVL72:$0.038 |
| tok/s/MW | B300:32218854GB300 NVL72:39310087 | B300:11988709GB300 NVL72:18660145 | B300:4992047GB300 NVL72:7920446 |
| Concurrency | B300:~40GB300 NVL72:~48 | B300:~12GB300 NVL72:~21 | B300:~4GB300 NVL72:~8 |
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.
