Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and B300 (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
At 142 tok/s/user interactivity on MiniMax M3.1 Flash 428B, B200 delivers 58986 tok/s/chip at $0.01 per million tokens; B300 delivers 61323 tok/s/chip at $0.01. B200 is 26% cheaper per token; B300 delivers 4% more tok/s/chip at this point.
B200 posts 32539 tok/s/chip for $0.01 per million tokens at 278 tok/s/user on MiniMax M3.1 Flash 428B; B300 posts 23011 tok/s/chip for $0.03. B200 is 85% cheaper per token; B200 delivers 41% more tok/s/chip.
Throughput at 414 tok/s/user on MiniMax M3.1 Flash 428B: B200 hits 15014 tok/s/chip, B300 hits 9547. Per-million costs land at $0.03 and $0.07 respectively. B200 is 105% cheaper per token; B200 delivers 57% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:58986.4B300:61322.9 | B200:32539.5B300:23011.0 | B200:15013.7B300:9546.8 |
| Cost ($/M tok) | B200:$0.008B300:$0.010 | B200:$0.015B300:$0.027 | B200:$0.032B300:$0.066 |
| tok/s/MW | B200:34494965B300:32275212 | B200:19028922B300:12111055 | B200:8779943B300:5024651 |
| Concurrency | B200:~32B300:~41 | B200:~18B300:~12 | B200:~7B300:~4 |
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.
