Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) 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.
Near the low end of the 38–255 tok/s/user interactivity band, at 92 tok/s/user on gpt-oss 120B: H200 runs 6714 tok/s/chip at $0.05/M tokens, MI355X runs 26412 at $0.02/M. MI355X is 220% cheaper per token; MI355X delivers 293% more tok/s/chip.
Setting 147 tok/s/user as the target on gpt-oss 120B, H200 produces 4482 tok/s/chip ($0.08 per million tokens) and MI355X produces 16069 ($0.03). MI355X is 192% cheaper per token; MI355X delivers 259% more tok/s/chip.
At 201 tok/s/user interactivity on gpt-oss 120B, H200 delivers 2812 tok/s/chip at $0.12 per million tokens; MI355X delivers 10455 tok/s/chip at $0.04. MI355X is 202% cheaper per token; MI355X delivers 272% more tok/s/chip at this point. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H200:6714.1MI355X:26411.7 | H200:4481.8MI355X:16069.1 | H200:2811.5MI355X:10454.6 |
| Cost ($/M tok) | H200:$0.050MI355X:$0.016 | H200:$0.076MI355X:$0.026 | H200:$0.121MI355X:$0.040 |
| tok/s/MW | H200:4900797MI355X:12637175 | H200:3271417MI355X:7688576 | H200:2052199MI355X:5002206 |
| Concurrency | H200:~17MI355X:~34 | H200:~16MI355X:~13 | H200:~6MI355X:~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.
gpt-oss 120B 8K / 1K Total Tokens per $1 TCO vs. Interactivity