MiniMax M3 428B · Chip comparison
MiniMax M3 428B — H200 vs Vera Rubin NVL72
Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) and Vera Rubin NVL72 (NVIDIA Vera Rubin) on MiniMax M3 428B. 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.
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 →
Vera Rubin NVL72 hits 112,936 tok/s/chip for $0.009 per million tokens at 314 tok/s/user on MiniMax M3 428B. No H200 data at this operating point.
Vera Rubin NVL72: 38,092 tok/s/chip, $0.026 per million tokens at 527 tok/s/user on MiniMax M3 428B. H200 is unmeasured here.
At 740 tok/s/user on MiniMax M3 428B, Vera Rubin NVL72 delivers 27,827 tok/s/chip at $0.036 per million tokens; H200 hasn't been benchmarked at this target. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H200—Vera Rubin NVL72112,936 | H200—Vera Rubin NVL7238,092 | H200—Vera Rubin NVL7227,827 |
| Cost ($/M tok) | H200—Vera Rubin NVL72$0.009 | H200—Vera Rubin NVL72$0.026 | H200—Vera Rubin NVL72$0.036 |
| tok/s/MW | H200—Vera Rubin NVL7234,222,898 | H200—Vera Rubin NVL7211,543,003 | H200—Vera Rubin NVL728,432,334 |
| Concurrency | H200—Vera Rubin NVL72~32 | H200—Vera Rubin NVL72~52 | H200—Vera Rubin NVL72~37 |