MiniMax M3 428B · Chip comparison
MiniMax M3 428B — B300 vs GB200 NVL72
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and GB200 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 →
B300 posts 42,257 tok/s/chip for $0.015 per million tokens at 168 tok/s/user on MiniMax M3 428B; GB200 NVL72 posts 33,531 tok/s/chip for $0.015. B300 is 4% cheaper per token; B300 delivers 26% more tok/s/chip.
Throughput at 253 tok/s/user on MiniMax M3 428B: B300 hits 14,212 tok/s/chip, GB200 NVL72 hits 16,343. Costs per million tokens land at $0.044 and $0.032 respectively. GB200 NVL72 is 28% cheaper per token; GB200 NVL72 delivers 15% more tok/s/chip.
B300 / GB200 NVL72 on MiniMax M3 428B at 338 tok/s/user: 5,232 / 8,176 tok/s/chip, $0.12 / $0.063 per million tokens. GB200 NVL72 is 47% cheaper per token; GB200 NVL72 delivers 56% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B30042,257GB200 NVL7233,531 | B30014,212GB200 NVL7216,343 | B3005,232GB200 NVL728,176 |
| Cost ($/M tok) | B300$0.015GB200 NVL72$0.015 | B300$0.044GB200 NVL72$0.032 | B300$0.12GB200 NVL72$0.063 |
| tok/s/MW | B30022,240,703GB200 NVL7217,930,819 | B3007,479,768GB200 NVL728,739,563 | B3002,753,772GB200 NVL724,372,272 |
| Concurrency | B300~25GB200 NVL72~19 | B300~8GB200 NVL72~9 | B300~5GB200 NVL72~2 |