MiniMax M2.5/M2.7 · Chip comparison
MiniMax M2.5/M2.7 — B200 vs MI355X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) 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 14–110 tok/s/user interactivity band, at 37 tok/s/user on MiniMax M2.5/M2.7: B200 runs 10,432 tok/s/chip at $0.046 per million tokens, MI355X runs 5,356 at $0.078. B200 is 41% cheaper per token; B200 delivers 95% more tok/s/chip.
Setting 62 tok/s/user as the target on MiniMax M2.5/M2.7, B200 produces 5,345 tok/s/chip ($0.090 per million tokens) and MI355X produces 3,138 ($0.13). B200 is 32% cheaper per token; B200 delivers 70% more tok/s/chip.
At 86 tok/s/user interactivity on MiniMax M2.5/M2.7, B200 delivers 3,213 tok/s/chip at $0.15 per million tokens; MI355X delivers 1,954 tok/s/chip at $0.21. B200 is 30% cheaper per token; B200 delivers 64% more tok/s/chip at this point. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B20010,432MI355X5,356 | B2005,345MI355X3,138 | B2003,213MI355X1,954 |
| Cost ($/M tok) | B200$0.046MI355X$0.078 | B200$0.090MI355X$0.13 | B200$0.15MI355X$0.21 |
| tok/s/MW | B2006,100,788MI355X2,562,481 | B2003,125,935MI355X1,501,464 | B2001,878,801MI355X934,901 |
| Concurrency | B200~777MI355X~67 | B200~62MI355X~11 | B200~25MI355X~5 |