Head-to-head AI inference benchmark comparison of H100 (NVIDIA Hopper) 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
At 48 tok/s/user interactivity on Muse Spark Open 816B, H100 delivers 1316 tok/s/chip at $0.25 per million tokens; H200 delivers 6378 tok/s/chip at $0.05. H200 is 365% cheaper per token; H200 delivers 385% more tok/s/chip at this point.
H100 posts 1316 tok/s/chip for $0.25 per million tokens at 88 tok/s/user on Muse Spark Open 816B; H200 posts 4947 tok/s/chip for $0.07. H200 is 261% cheaper per token; H200 delivers 276% more tok/s/chip.
Throughput at 127 tok/s/user on Muse Spark Open 816B: H100 hits 1316 tok/s/chip, H200 hits 3485. Per-million costs land at $0.25 and $0.10 respectively. H200 is 154% cheaper per token; H200 delivers 165% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H100:1315.8H200:6377.7 | H100:1315.8H200:4946.5 | H100:1315.8H200:3484.6 |
| Cost ($/M tok) | H100:$0.247H200:$0.053 | H100:$0.247H200:$0.069 | H100:$0.247H200:$0.097 |
| tok/s/MW | H100:960474H200:4655246 | H100:960474H200:3610586 | H100:960474H200:2543511 |
| Concurrency | H100:~1H200:~14 | H100:~1H200:~9 | H100:~1H200:~6 |
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.
