Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) and MI325X (AMD CDNA 3) on MiniMax M3 428B. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics β same interactions as the main inference chart.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX β
Near the low end of the 11β281 tok/s/user interactivity band, at 78 tok/s/user on MiniMax M3 428B: H200 runs 8926 tok/s/chip at $0.04/M tokens, MI325X runs 864 at $0.35/M. H200 is 831% cheaper per token; H200 delivers 933% more tok/s/chip.
Setting 146 tok/s/user as the target on MiniMax M3 428B, H200 produces 7800 tok/s/chip ($0.04 per million tokens) and MI325X produces 864 ($0.35). H200 is 714% cheaper per token; H200 delivers 803% more tok/s/chip.
At 214 tok/s/user interactivity on MiniMax M3 428B, H200 delivers 3815 tok/s/chip at $0.09 per million tokens; MI325X delivers 864 tok/s/chip at $0.35. H200 is 298% cheaper per token; H200 delivers 341% more tok/s/chip at this point. (Numbers reflect the default agentic-traces Β· fp8 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H200:8925.9MI325X:864.3 | H200:7800.4MI325X:864.3 | H200:3814.5MI325X:864.3 |
| Cost ($/M tok) | H200:$0.038MI325X:$0.354 | H200:$0.043MI325X:$0.354 | H200:$0.089MI325X:$0.354 |
| tok/s/MW | H200:6515256MI325X:511396 | H200:5693758MI325X:511396 | H200:2784341MI325X:511396 |
| Concurrency | H200:~14MI325X:~1 | H200:~10MI325X:~1 | H200:~4MI325X:~1 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
