Kimi K3.1 Pro — B200 vs MI355X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on Kimi K3.1 Pro. 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Near the low end of the 27–83 tok/s/user interactivity band, at 41 tok/s/user on Kimi K3.1 Pro: B200 runs 2685 tok/s/chip at $0.18/M tokens, MI355X runs 15239 at $0.03/M. MI355X is 555% cheaper per token; MI355X delivers 468% more tok/s/chip.
Setting 55 tok/s/user as the target on Kimi K3.1 Pro, B200 produces 1838 tok/s/chip ($0.26 per million tokens) and MI355X produces 11318 ($0.04). MI355X is 610% cheaper per token; MI355X delivers 516% more tok/s/chip.
At 69 tok/s/user interactivity on Kimi K3.1 Pro, B200 delivers 1544 tok/s/chip at $0.31 per million tokens; MI355X delivers 7991 tok/s/chip at $0.05. MI355X is 497% cheaper per token; MI355X delivers 418% more tok/s/chip at this point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:2685.1MI355X:15239.1 | B200:1837.9MI355X:11317.9 | B200:1543.7MI355X:7991.0 |
| Cost ($/M tok) | B200:$0.179MI355X:$0.027 | B200:$0.261MI355X:$0.037 | B200:$0.311MI355X:$0.052 |
| tok/s/MW | B200:1570224MI355X:7291450 | B200:1074770MI355X:5415266 | B200:902756MI355X:3823450 |
| Concurrency | B200:~12MI355X:~29 | B200:~7MI355X:~20 | B200:~5MI355X:~13 |