MiniMax M2.5/M2.7 — B200 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and GB300 NVL72 (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.
Near the low end of the 30–186 tok/s/user interactivity band, at 69 tok/s/user on MiniMax M2.5/M2.7: B200 runs 7991 tok/s/GPU at $0.07/M tokens, GB300 NVL72 runs 8401 at $0.08/M. B200 is 23% cheaper per token; GB300 NVL72 delivers 5% more tok/s/GPU.
Setting 108 tok/s/user as the target on MiniMax M2.5/M2.7, B200 produces 2908 tok/s/GPU ($0.19 per million tokens) and GB300 NVL72 produces 3059 ($0.24). B200 is 29% cheaper per token; GB300 NVL72 delivers 5% more tok/s/GPU.
At 147 tok/s/user interactivity on MiniMax M2.5/M2.7, B200 delivers 1138 tok/s/GPU at $0.48 per million tokens; GB300 NVL72 delivers 1009 tok/s/GPU at $0.73. B200 is 53% cheaper per token; B200 delivers 13% more tok/s/GPU at this point. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:7991.5GB300 NVL72:8401.0 | B200:2908.4GB300 NVL72:3058.6 | B200:1137.8GB300 NVL72:1008.6 |
| Cost ($/M tok) | B200:$0.068GB300 NVL72:$0.084 | B200:$0.186GB300 NVL72:$0.241 | B200:$0.476GB300 NVL72:$0.727 |
| tok/s/MW | B200:3682704GB300 NVL72:4000464 | B200:1340265GB300 NVL72:1456484 | B200:524351GB300 NVL72:480294 |
| Concurrency | B200:~711GB300 NVL72:~1024 | B200:~128GB300 NVL72:~121 | B200:~4GB300 NVL72:~22 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.