Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on DeepSeek R1. 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 interactivity on DeepSeek R1, B300 delivers 5239 tok/s/chip at $0.12 per million tokens; MI355X delivers 1876 tok/s/chip at $0.22. B300 is 85% cheaper per token; B300 delivers 179% more tok/s/chip at this point.
B300 posts 1540 tok/s/chip for $0.41 per million tokens at 108 tok/s/user on DeepSeek R1; MI355X posts 1032 tok/s/chip for $0.40. Cost per token is essentially tied; B300 delivers 49% more tok/s/chip.
Throughput at 156 tok/s/user on DeepSeek R1: B300 hits 788 tok/s/chip, MI355X hits 766. Per-million costs land at $0.80 and $0.54 respectively. MI355X is 46% cheaper per token; B300 delivers 3% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:5239.1MI355X:1875.9 | B300:1540.2MI355X:1031.9 | B300:788.5MI355X:766.4 |
| Cost ($/M tok) | B300:$0.120MI355X:$0.222 | B300:$0.408MI355X:$0.404 | B300:$0.796MI355X:$0.544 |
| tok/s/MW | B300:2757405MI355X:897537 | B300:810658MI355X:493741 | B300:414999MI355X:366711 |
| Concurrency | B300:~195MI355X:~35 | B300:~41MI355X:~27 | B300:~4MI355X:~4 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
TCO $/chip/hr: VR200: 3.61H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68Jalapeño (Teacup): 1.47
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
1 The ATOM engine is promising, however it has yet to serve production tokens. It is still in its infant stage.
DeepSeek R1 0528 671B 8K / 1K Total Tokens per $1 TCO vs. Interactivity