Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and H200 (NVIDIA Hopper) on DeepSeek V4.1 Flash 552B. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — 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 →
Setting 10 tok/s/user as the target on DeepSeek V4.1 Flash 552B, GB300 NVL72 produces 18819 tok/s/chip ($0.03 per million tokens) and H200 produces 19341 ($0.02). H200 is 95% cheaper per token; H200 delivers 3% more tok/s/chip.
At 14 tok/s/user interactivity on DeepSeek V4.1 Flash 552B, GB300 NVL72 delivers 14999 tok/s/chip at $0.04 per million tokens; H200 delivers 19341 tok/s/chip at $0.02. H200 is 144% cheaper per token; H200 delivers 29% more tok/s/chip at this point.
GB300 NVL72 posts 12449 tok/s/chip for $0.05 per million tokens at 18 tok/s/user on DeepSeek V4.1 Flash 552B; H200 posts 19283 tok/s/chip for $0.02. H200 is 193% cheaper per token; H200 delivers 55% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB300 NVL72:18818.6H200:19341.2 | GB300 NVL72:14999.5H200:19341.2 | GB300 NVL72:12449.2H200:19282.5 |
| Cost ($/M tok) | GB300 NVL72:$0.034H200:$0.018 | GB300 NVL72:$0.043H200:$0.018 | GB300 NVL72:$0.052H200:$0.018 |
| tok/s/MW | GB300 NVL72:8876708H200:14117634 | GB300 NVL72:7075216H200:14117634 | GB300 NVL72:5872271H200:14074818 |
| Concurrency | GB300 NVL72:~39H200:~64 | GB300 NVL72:~25H200:~64 | GB300 NVL72:~19H200:~57 |
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.
