Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on MiniMax M2.5/M2.7. 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.
B300 / MI355X on MiniMax M2.5/M2.7 at 37 tok/s/user: 11384 / 5356 tok/s/chip, $0.06 / $0.08 per million tokens. B300 is 41% cheaper per token; B300 delivers 113% more tok/s/chip.
Around the middle of the 14–110 tok/s/user interactivity band, at 62 tok/s/user on MiniMax M2.5/M2.7: B300 runs 6912 tok/s/chip at $0.09/M tokens, MI355X runs 3138 at $0.13/M. B300 is 46% cheaper per token; B300 delivers 120% more tok/s/chip.
Setting 86 tok/s/user as the target on MiniMax M2.5/M2.7, B300 produces 4098 tok/s/chip ($0.15 per million tokens) and MI355X produces 1954 ($0.21). B300 is 39% cheaper per token; B300 delivers 110% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:11383.6MI355X:5355.6 | B300:6912.0MI355X:3138.1 | B300:4098.2MI355X:1953.9 |
| Cost ($/M tok) | B300:$0.055MI355X:$0.078 | B300:$0.091MI355X:$0.133 | B300:$0.153MI355X:$0.213 |
| tok/s/MW | B300:5991384MI355X:2562481 | B300:3637897MI355X:1501464 | B300:2156939MI355X:934901 |
| Concurrency | B300:~512MI355X:~67 | B300:~512MI355X:~11 | B300:~5MI355X:~5 |
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.
MiniMax M2.5/2.7 230B 8K / 1K Total Tokens per $1 TCO vs. Interactivity