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 66 tok/s/user on MiniMax M2.5/M2.7: B200 hits 8554 tok/s/GPU, B300 hits 7415. Per-million costs land at $0.06 and $0.09 respectively. B200 is 40% cheaper per token; B200 delivers 15% more tok/s/GPU.
B200 / B300 on MiniMax M2.5/M2.7 at 110 tok/s/user: 2744 / 2602 tok/s/GPU, $0.20 / $0.25 per million tokens. B200 is 26% cheaper per token; B200 delivers 5% more tok/s/GPU.
Toward the upper edge of the 22–197 tok/s/user interactivity band, at 154 tok/s/user on MiniMax M2.5/M2.7: B200 runs 772 tok/s/GPU at $0.71/M tokens, B300 runs 790 at $0.82/M. B200 is 16% cheaper per token; B300 delivers 2% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:8553.8B300:7414.7 | B200:2744.2B300:2602.4 | B200:772.0B300:790.4 |
| Cost ($/M tok) | B200:$0.063B300:$0.088 | B200:$0.198B300:$0.250 | B200:$0.710B300:$0.821 |
| tok/s/MW | B200:3941866B300:3416892 | B200:1264605B300:1199260 | B200:355765B300:364245 |
| Concurrency | B200:~1000B300:~524 | B200:~128B300:~68 | B200:~12B300:~14 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.