Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and H100 (NVIDIA Hopper) on Muse Spark Open 816B. 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 105 tok/s/user interactivity on Muse Spark Open 816B, B200 delivers 21796 tok/s/chip at $0.02 per million tokens; H100 delivers 1316 tok/s/chip at $0.25. B200 is 1020% cheaper per token; B200 delivers 1556% more tok/s/chip at this point.
B200 posts 18832 tok/s/chip for $0.03 per million tokens at 125 tok/s/user on Muse Spark Open 816B; H100 posts 1316 tok/s/chip for $0.25. B200 is 868% cheaper per token; B200 delivers 1331% more tok/s/chip.
Throughput at 146 tok/s/user on Muse Spark Open 816B: B200 hits 15803 tok/s/chip, H100 hits 1316. Per-million costs land at $0.03 and $0.25 respectively. B200 is 712% cheaper per token; B200 delivers 1101% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:21795.9H100:1315.8 | B200:18831.9H100:1315.8 | B200:15802.6H100:1315.8 |
| Cost ($/M tok) | B200:$0.022H100:$0.247 | B200:$0.026H100:$0.247 | B200:$0.030H100:$0.247 |
| tok/s/MW | B200:12746137H100:960474 | B200:11012788H100:960474 | B200:9241278H100:960474 |
| Concurrency | B200:~38H100:~1 | B200:~30H100:~1 | B200:~22H100:~1 |
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.
