MiniMax M2.5/M2.7 — B200 vs H200
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and H200 (NVIDIA Hopper) 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.
B200 posts 9617 tok/s/GPU for $0.06 per million tokens at 43 tok/s/user on MiniMax M2.5/M2.7; H200 posts 2816 tok/s/GPU for $0.14. B200 is 146% cheaper per token; B200 delivers 241% more tok/s/GPU.
Throughput at 72 tok/s/user on MiniMax M2.5/M2.7: B200 hits 3893 tok/s/GPU, H200 hits 1855. Per-million costs land at $0.14 and $0.21 respectively. B200 is 47% cheaper per token; B200 delivers 110% more tok/s/GPU.
B200 / H200 on MiniMax M2.5/M2.7 at 102 tok/s/user: 2080 / 1011 tok/s/GPU, $0.26 / $0.38 per million tokens. B200 is 46% cheaper per token; B200 delivers 106% more tok/s/GPU. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:9616.9H200:2816.4 | B200:3893.2H200:1855.1 | B200:2080.0H200:1011.3 |
| Cost ($/M tok) | B200:$0.056H200:$0.139 | B200:$0.142H200:$0.209 | B200:$0.261H200:$0.381 |
| tok/s/MW | B200:4431743H200:1628001 | B200:1794121H200:1072314 | B200:958524H200:584552 |
| Concurrency | B200:~582H200:~30 | B200:~32H200:~12 | B200:~15H200:~5 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.