MiniMax M3 428B · Chip comparison
MiniMax M3 428B — GB200 NVL72 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) 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 →
GB200 NVL72 posts 35,037 tok/s/chip for $0.015 per million tokens at 159 tok/s/user on MiniMax M3 428B; GB300 NVL72 posts 32,568 tok/s/chip for $0.020. GB200 NVL72 is 25% cheaper per token; GB200 NVL72 delivers 8% more tok/s/chip.
Throughput at 218 tok/s/user on MiniMax M3 428B: GB200 NVL72 hits 22,706 tok/s/chip, GB300 NVL72 hits 21,832. Costs per million tokens land at $0.023 and $0.029 respectively. GB200 NVL72 is 23% cheaper per token; GB200 NVL72 delivers 4% more tok/s/chip.
GB200 NVL72 / GB300 NVL72 on MiniMax M3 428B at 277 tok/s/user: 13,299 / 13,103 tok/s/chip, $0.039 / $0.049 per million tokens. GB200 NVL72 is 21% cheaper per token; GB200 NVL72 delivers 1% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GB300 NVL72 vs GB200 NVL72: full specs & benchmarks across models →
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL7235,037GB300 NVL7232,568 | GB200 NVL7222,706GB300 NVL7221,832 | GB200 NVL7213,299GB300 NVL7213,103 |
| Cost ($/M tok) | GB200 NVL72$0.015GB300 NVL72$0.020 | GB200 NVL72$0.023GB300 NVL72$0.029 | GB200 NVL72$0.039GB300 NVL72$0.049 |
| tok/s/MW | GB200 NVL7218,736,255GB300 NVL7215,362,054 | GB200 NVL7212,142,269GB300 NVL7210,298,334 | GB200 NVL727,111,534GB300 NVL726,180,856 |
| Concurrency | GB200 NVL72~20GB300 NVL72~29 | GB200 NVL72~13GB300 NVL72~20 | GB200 NVL72~7GB300 NVL72~24 |