Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and H200 (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
Setting 110 tok/s/user as the target on Muse Spark Open 816B, B200 produces 20951 tok/s/chip ($0.02 per million tokens) and H200 produces 4116 ($0.08). B200 is 259% cheaper per token; B200 delivers 409% more tok/s/chip.
At 135 tok/s/user interactivity on Muse Spark Open 816B, B200 delivers 17741 tok/s/chip at $0.03 per million tokens; H200 delivers 3167 tok/s/chip at $0.11. B200 is 295% cheaper per token; B200 delivers 460% more tok/s/chip at this point.
B200 posts 12278 tok/s/chip for $0.04 per million tokens at 161 tok/s/user on Muse Spark Open 816B; H200 posts 1802 tok/s/chip for $0.19. B200 is 381% cheaper per token; B200 delivers 582% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:20951.1H200:4116.2 | B200:17741.2H200:3167.4 | B200:12278.2H200:1801.6 |
| Cost ($/M tok) | B200:$0.023H200:$0.082 | B200:$0.027H200:$0.107 | B200:$0.039H200:$0.188 |
| tok/s/MW | B200:12252129H200:3004490 | B200:10374983H200:2311960 | B200:7180236H200:1315011 |
| Concurrency | B200:~36H200:~7 | B200:~26H200:~6 | B200:~17H200:~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.
