Head-to-head AI inference benchmark comparison of MI325X (AMD CDNA 3) and Vera Rubin NVL72 (NVIDIA Vera Rubin) on GLM 5.3 744B. 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
At 18 tok/s/user on GLM 5.3 744B, MI325X delivers 1529 tok/s/chip at $0.20 per million tokens; Vera Rubin NVL72 hasn't been benchmarked at this target.
MI325X hits 1222 tok/s/chip for $0.25 per million tokens at 35 tok/s/user on GLM 5.3 744B. No Vera Rubin NVL72 data at this operating point.
MI325X: 1211 tok/s/chip, $0.25 per million tokens at 53 tok/s/user on GLM 5.3 744B. Vera Rubin NVL72 is unmeasured here. (Numbers reflect the default agentic-traces Β· fp8 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MI325X:1529.4Vera Rubin NVL72:β | MI325X:1222.1Vera Rubin NVL72:β | MI325X:1210.7Vera Rubin NVL72:β |
| Cost ($/M tok) | MI325X:$0.200Vera Rubin NVL72:β | MI325X:$0.250Vera Rubin NVL72:β | MI325X:$0.252Vera Rubin NVL72:β |
| tok/s/MW | MI325X:904946Vera Rubin NVL72:β | MI325X:723114Vera Rubin NVL72:β | MI325X:716379Vera Rubin NVL72:β |
| Concurrency | MI325X:~3Vera Rubin NVL72:β | MI325X:~2Vera Rubin NVL72:β | MI325X:~1Vera Rubin NVL72:β |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.
