Kimi K2.5/K2.6/K2.7-Code 1T — B200 vs MI325X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI325X (AMD CDNA 3) 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.
B200 posts 2078 tok/s/chip for $0.23 per million tokens at 34 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T; MI325X posts 316 tok/s/chip for $0.97. B200 is 318% cheaper per token; B200 delivers 558% more tok/s/chip.
Throughput at 38 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T: B200 hits 1883 tok/s/chip, MI325X hits 267. Per-million costs land at $0.26 and $1.14 respectively. B200 is 348% cheaper per token; B200 delivers 604% more tok/s/chip.
B200 / MI325X on Kimi K2.5/K2.6/K2.7-Code 1T at 42 tok/s/user: 1705 / 229 tok/s/chip, $0.28 / $1.33 per million tokens. B200 is 373% cheaper per token; B200 delivers 644% more tok/s/chip. (Numbers reflect the default 8k/1k · int4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:2077.7MI325X:315.9 | B200:1882.9MI325X:267.3 | B200:1705.0MI325X:229.1 |
| Cost ($/M tok) | B200:$0.231MI325X:$0.967 | B200:$0.255MI325X:$1.143 | B200:$0.282MI325X:$1.333 |
| tok/s/MW | B200:1215046MI325X:186945 | B200:1101114MI325X:158195 | B200:997077MI325X:135586 |
| Concurrency | B200:~54MI325X:~9 | B200:~45MI325X:~7 | B200:~37MI325X:~5 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Total Tokens per $1 USD (Owning - Hyperscaler) vs. Interactivity
Kimi K2.5/2.6/2.7-Code 1T • FP4 • 8K / 1K • Source: SemiAnalysis InferenceX™
TCO $/chip/hr: H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68
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.
No data available
Please change the model, sequence, precision, date range or chip selection.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip