Kimi K3.1 Pro — B200 vs B300
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and B300 (NVIDIA Blackwell) 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 14–83 tok/s/user interactivity band, at 31 tok/s/user on Kimi K3.1 Pro: B200 runs 2884 tok/s/chip at $0.17/M tokens, B300 runs 22877 at $0.03/M. B300 is 507% cheaper per token; B300 delivers 693% more tok/s/chip.
Setting 48 tok/s/user as the target on Kimi K3.1 Pro, B200 produces 2187 tok/s/chip ($0.22 per million tokens) and B300 produces 17165 ($0.04). B300 is 501% cheaper per token; B300 delivers 685% more tok/s/chip.
At 66 tok/s/user interactivity on Kimi K3.1 Pro, B200 delivers 1610 tok/s/chip at $0.30 per million tokens; B300 delivers 8146 tok/s/chip at $0.08. B300 is 287% cheaper per token; B300 delivers 406% more tok/s/chip at this point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:2884.4B300:22876.9 | B200:2186.9B300:17164.8 | B200:1609.9B300:8145.9 |
| Cost ($/M tok) | B200:$0.167B300:$0.027 | B200:$0.220B300:$0.037 | B200:$0.299B300:$0.077 |
| tok/s/MW | B200:1686807B300:12040462 | B200:1278916B300:9034110 | B200:941454B300:4287323 |
| Concurrency | B200:~14B300:~56 | B200:~9B300:~27 | B200:~6B300:~16 |