Head-to-head AI inference benchmark comparison of GB300 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.
GB300 NVL72: 10203 tok/s/chip, $0.06 per million tokens at 63 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T. H200 is unmeasured here.
At 103 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, GB300 NVL72 delivers 1685 tok/s/chip at $0.38 per million tokens; H200 hasn't been benchmarked at this target.
GB300 NVL72 hits 731 tok/s/chip for $0.88 per million tokens at 143 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T. No H200 data at this operating point. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB300 NVL72:10202.8H200:— | GB300 NVL72:1684.6H200:— | GB300 NVL72:731.1H200:— |
| Cost ($/M tok) | GB300 NVL72:$0.063H200:— | GB300 NVL72:$0.381H200:— | GB300 NVL72:$0.878H200:— |
| tok/s/MW | GB300 NVL72:4812653H200:— | GB300 NVL72:794621H200:— | GB300 NVL72:344856H200:— |
| Concurrency | GB300 NVL72:~1202H200:— | GB300 NVL72:~68H200:— | GB300 NVL72:~26H200:— |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
TCO $/chip/hr:
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
Matching measurements exist, but their chip series are hidden.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip
Kimi K2.5/2.6/2.7-Code 1T 8K / 1K Total Tokens per $1 TCO vs. Interactivity