Kimi K2.5/K2.6/K2.7-Code 1T · Chip comparison
Kimi K2.5/K2.6/K2.7-Code 1T — B200 vs H200
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and H200 (NVIDIA Hopper) 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.
B200 / H200 on Kimi K2.5/K2.6/K2.7-Code 1T at 45 tok/s/user: 1,588 / 821 tok/s/chip, $0.30 / $0.41 per million tokens. B200 is 27% cheaper per token; B200 delivers 93% more tok/s/chip.
Around the middle of the 30–92 tok/s/user interactivity band, at 61 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T: B200 runs 1,178 tok/s/chip at $0.41 per million tokens, H200 runs 673 at $0.50. B200 is 19% cheaper per token; B200 delivers 75% more tok/s/chip.
Setting 77 tok/s/user as the target on Kimi K2.5/K2.6/K2.7-Code 1T, B200 produces 824 tok/s/chip ($0.58 per million tokens) and H200 produces 530 ($0.64). B200 is 9% cheaper per token; B200 delivers 56% more tok/s/chip. (Numbers reflect the default 8k/1k · int4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B2001,588H200821 | B2001,178H200673 | B200824H200530 |
| Cost ($/M tok) | B200$0.30H200$0.41 | B200$0.41H200$0.50 | B200$0.58H200$0.64 |
| tok/s/MW | B200928,398H200599,258 | B200688,654H200491,168 | B200482,136H200386,505 |
| Concurrency | B200~32H200~17 | B200~17H200~10 | B200~10H200~6 |