Head-to-head AI inference benchmark comparison of B200 (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
Throughput at 139 tok/s/user on MiniMax M3.1 Flash 428B: B200 hits 58986 tok/s/chip, GB300 NVL72 hits 57954. Per-million costs land at $0.01 and $0.01 respectively. B200 is 36% cheaper per token; B200 delivers 2% more tok/s/chip.
B200 / GB300 NVL72 on MiniMax M3.1 Flash 428B at 260 tok/s/user: 26420 / 23583 tok/s/chip, $0.02 / $0.03 per million tokens. B200 is 50% cheaper per token; B200 delivers 12% more tok/s/chip.
Toward the upper edge of the 19β502 tok/s/user interactivity band, at 381 tok/s/user on MiniMax M3.1 Flash 428B: B200 runs 11733 tok/s/chip at $0.04/M tokens, GB300 NVL72 runs 13571 at $0.05/M. B200 is 15% cheaper per token; GB300 NVL72 delivers 16% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:58986.4GB300 NVL72:57953.6 | B200:26420.0GB300 NVL72:23583.3 | B200:11732.5GB300 NVL72:13571.1 |
| Cost ($/M tok) | B200:$0.008GB300 NVL72:$0.011 | B200:$0.018GB300 NVL72:$0.027 | B200:$0.041GB300 NVL72:$0.047 |
| tok/s/MW | B200:34494965GB300 NVL72:27336609 | B200:15450308GB300 NVL72:11124193 | B200:6861115GB300 NVL72:6401464 |
| Concurrency | B200:~32GB300 NVL72:~32 | B200:~15GB300 NVL72:~13 | B200:~6GB300 NVL72:~7 |
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.
