Kimi K2.5/K2.6/K2.7-Code 1T — GB200 NVL72 vs H200
Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and H200 (NVIDIA Hopper) on Kimi K2.5/K2.6/K2.7-Code 1T. 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.
At 60 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, GB200 NVL72 delivers 7627 tok/s/GPU at $0.08 per million tokens; H200 hasn't been benchmarked at this target.
GB200 NVL72 hits 451 tok/s/GPU for $1.41 per million tokens at 102 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T. No H200 data at this operating point.
GB200 NVL72: 192 tok/s/GPU, $3.15 per million tokens at 144 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T. H200 is unmeasured here. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB200 NVL72:7626.9H200:— | GB200 NVL72:451.0H200:— | GB200 NVL72:192.1H200:— |
| Cost ($/M tok) | GB200 NVL72:$0.080H200:— | GB200 NVL72:$1.407H200:— | GB200 NVL72:$3.151H200:— |
| tok/s/MW | GB200 NVL72:3631859H200:— | GB200 NVL72:214751H200:— | GB200 NVL72:91476H200:— |
| Concurrency | GB200 NVL72:~3340H200:— | GB200 NVL72:~98H200:— | GB200 NVL72:~28H200:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.