Kimi K2.5/K2.6/K2.7-Code 1T — B200 vs MI300X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI300X (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.
Throughput at 33 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T: B200 hits 2128 tok/s/chip, MI300X hits 255. Per-million costs land at $0.23 and $1.03 respectively. B200 is 358% cheaper per token; B200 delivers 734% more tok/s/chip.
B200 / MI300X on Kimi K2.5/K2.6/K2.7-Code 1T at 37 tok/s/user: 1930 / 224 tok/s/chip, $0.25 / $1.18 per million tokens. B200 is 374% cheaper per token; B200 delivers 764% more tok/s/chip.
Toward the upper edge of the 30–43 tok/s/user interactivity band, at 40 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T: B200 runs 1791 tok/s/chip at $0.27/M tokens, MI300X runs 206 at $1.28/M. B200 is 378% cheaper per token; B200 delivers 771% more tok/s/chip. (Numbers reflect the default 8k/1k · int4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:2128.1MI300X:255.2 | B200:1930.3MI300X:223.5 | B200:1791.3MI300X:205.7 |
| Cost ($/M tok) | B200:$0.226MI300X:$1.034 | B200:$0.249MI300X:$1.181 | B200:$0.268MI300X:$1.283 |
| tok/s/MW | B200:1244519MI300X:183608 | B200:1128855MI300X:160804 | B200:1047563MI300X:147958 |
| Concurrency | B200:~56MI300X:~7 | B200:~47MI300X:~5 | B200:~41MI300X:~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