Head-to-head AI inference benchmark comparison of MI300X (AMD CDNA 3) and MI355X (AMD CDNA 4) on gpt-oss 120B. 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.
Setting 90 tok/s/user as the target on gpt-oss 120B, MI300X produces 5095 tok/s/chip ($0.05 per million tokens) and MI355X produces 27009 ($0.02). MI355X is 236% cheaper per token; MI355X delivers 430% more tok/s/chip.
At 142 tok/s/user interactivity on gpt-oss 120B, MI300X delivers 3406 tok/s/chip at $0.08 per million tokens; MI355X delivers 16764 tok/s/chip at $0.02. MI355X is 212% cheaper per token; MI355X delivers 392% more tok/s/chip at this point.
MI300X posts 1102 tok/s/chip for $0.24 per million tokens at 194 tok/s/user on gpt-oss 120B; MI355X posts 10948 tok/s/chip for $0.04. MI355X is 529% cheaper per token; MI355X delivers 894% more tok/s/chip. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MI300X:5094.8MI355X:27008.6 | MI300X:3405.7MI355X:16763.8 | MI300X:1101.8MI355X:10948.1 |
| Cost ($/M tok) | MI300X:$0.052MI355X:$0.015 | MI300X:$0.077MI355X:$0.025 | MI300X:$0.240MI355X:$0.038 |
| tok/s/MW | MI300X:3665334MI355X:12922781 | MI300X:2450139MI355X:8020942 | MI300X:792671MI355X:5238331 |
| Concurrency | MI300X:~13MI355X:~35 | MI300X:~5MI355X:~14 | MI300X:~7MI355X:~6 |
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.
gpt-oss 120B 8K / 1K Total Tokens per $1 TCO vs. Interactivity