Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and H100 (NVIDIA Hopper) 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
Near the low end of the 19β288 tok/s/user interactivity band, at 86 tok/s/user on MiniMax M3.1 Flash 428B: B200 runs 58986 tok/s/chip at $0.01/M tokens, H100 runs 5714 at $0.06/M. B200 is 598% cheaper per token; B200 delivers 932% more tok/s/chip.
Setting 153 tok/s/user as the target on MiniMax M3.1 Flash 428B, B200 produces 58986 tok/s/chip ($0.01 per million tokens) and H100 produces 4465 ($0.07). B200 is 794% cheaper per token; B200 delivers 1221% more tok/s/chip.
At 221 tok/s/user interactivity on MiniMax M3.1 Flash 428B, B200 delivers 37004 tok/s/chip at $0.01 per million tokens; H100 delivers 3544 tok/s/chip at $0.09. B200 is 606% cheaper per token; B200 delivers 944% more tok/s/chip at this point. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:58986.4H100:5713.6 | B200:58986.4H100:4464.6 | B200:37004.3H100:3544.3 |
| Cost ($/M tok) | B200:$0.008H100:$0.057 | B200:$0.008H100:$0.073 | B200:$0.013H100:$0.092 |
| tok/s/MW | B200:34494965H100:4170496 | B200:34494965H100:3258831 | B200:21639946H100:2587074 |
| Concurrency | B200:~32H100:~9 | B200:~32H100:~7 | B200:~20H100:~3 |
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.
