MiniMax M2.5/M2.7 · Chip comparison
MiniMax M2.5/M2.7 — B200 vs B300
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and B300 (NVIDIA Blackwell) on MiniMax M2.5/M2.7. 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.
Throughput at 60 tok/s/user on MiniMax M2.5/M2.7: B200 hits 13,123 tok/s/chip, B300 hits 13,222. Costs per million tokens land at $0.037 and $0.047 respectively. B200 is 23% cheaper per token; throughput per chip is essentially tied.
B200 / B300 on MiniMax M2.5/M2.7 at 101 tok/s/user: 6,649 / 6,697 tok/s/chip, $0.072 / $0.094 per million tokens. B200 is 23% cheaper per token; throughput per chip is essentially tied.
Toward the upper edge of the 19–183 tok/s/user interactivity band, at 143 tok/s/user on MiniMax M2.5/M2.7: B200 runs 3,074 tok/s/chip at $0.16 per million tokens, B300 runs 2,915 at $0.22. B200 is 27% cheaper per token; B200 delivers 5% more tok/s/chip. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B20013,123B30013,222 | B2006,649B3006,697 | B2003,074B3002,915 |
| Cost ($/M tok) | B200$0.037B300$0.047 | B200$0.072B300$0.094 | B200$0.16B300$0.22 |
| tok/s/MW | B2007,674,471B3006,958,818 | B2003,888,345B3003,524,994 | B2001,797,369B3001,534,289 |
| Concurrency | B200~787B300~295 | B200~9B300~9 | B200~11B300~11 |