Kimi K2.5/K2.6/K2.7-Code 1T · Chip comparison
Kimi K2.5/K2.6/K2.7-Code 1T — B200 vs MI355X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on Kimi K2.5/K2.6/K2.7-Code 1T. 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 11–123 tok/s/user interactivity band, at 38 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T: B200 runs 12,043 tok/s/chip at $0.040 per million tokens, MI355X runs 4,004 at $0.10. B200 is 62% cheaper per token; B200 delivers 3.0× the tok/s/chip.
Setting 67 tok/s/user as the target on Kimi K2.5/K2.6/K2.7-Code 1T, B200 produces 3,662 tok/s/chip ($0.13 per million tokens) and MI355X produces 2,493 ($0.17). B200 is 21% cheaper per token; B200 delivers 47% more tok/s/chip.
At 95 tok/s/user interactivity on Kimi K2.5/K2.6/K2.7-Code 1T, B200 delivers 1,643 tok/s/chip at $0.29 per million tokens; MI355X delivers 1,739 tok/s/chip at $0.24. MI355X is 18% cheaper per token; MI355X delivers 6% more tok/s/chip at this point. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B20012,043MI355X4,004 | B2003,662MI355X2,493 | B2001,643MI355X1,739 |
| Cost ($/M tok) | B200$0.040MI355X$0.10 | B200$0.13MI355X$0.17 | B200$0.29MI355X$0.24 |
| tok/s/MW | B2007,042,449MI355X1,915,595 | B2002,141,577MI355X1,192,676 | B200961,048MI355X831,906 |
| Concurrency | B200~736MI355X~102 | B200~178MI355X~17 | B200~9MI355X~9 |