Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) and Vera Rubin NVL72 (NVIDIA Vera Rubin) on GLM 5.3 744B. 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 122 tok/s/user on GLM 5.3 744B, H200 delivers 2769 tok/s/chip at $0.12 per million tokens; Vera Rubin NVL72 hasn't been benchmarked at this target.
H200 hits 2306 tok/s/chip for $0.15 per million tokens at 134 tok/s/user on GLM 5.3 744B. No Vera Rubin NVL72 data at this operating point.
H200: 1545 tok/s/chip, $0.22 per million tokens at 147 tok/s/user on GLM 5.3 744B. Vera Rubin NVL72 is unmeasured here. (Numbers reflect the default agentic-traces Β· fp8 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H200:2768.5Vera Rubin NVL72:β | H200:2305.6Vera Rubin NVL72:β | H200:1545.1Vera Rubin NVL72:β |
| Cost ($/M tok) | H200:$0.122Vera Rubin NVL72:β | H200:$0.147Vera Rubin NVL72:β | H200:$0.219Vera Rubin NVL72:β |
| tok/s/MW | H200:2020825Vera Rubin NVL72:β | H200:1682909Vera Rubin NVL72:β | H200:1127835Vera Rubin NVL72:β |
| Concurrency | H200:~12Vera Rubin NVL72:β | H200:~9Vera Rubin NVL72:β | H200:~5Vera Rubin NVL72:β |
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.
