Kimi K3.1 Pro — B300 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and GB300 NVL72 (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 →
Setting 106 tok/s/user as the target on Kimi K3.1 Pro, B300 produces 6118 tok/s/chip ($0.10 per million tokens) and GB300 NVL72 produces 15002 ($0.04). GB300 NVL72 is 140% cheaper per token; GB300 NVL72 delivers 145% more tok/s/chip.
At 151 tok/s/user interactivity on Kimi K3.1 Pro, B300 delivers 4760 tok/s/chip at $0.13 per million tokens; GB300 NVL72 delivers 9188 tok/s/chip at $0.07. GB300 NVL72 is 89% cheaper per token; GB300 NVL72 delivers 93% more tok/s/chip at this point.
B300 posts 2961 tok/s/chip for $0.21 per million tokens at 196 tok/s/user on Kimi K3.1 Pro; GB300 NVL72 posts 5251 tok/s/chip for $0.12. GB300 NVL72 is 73% cheaper per token; GB300 NVL72 delivers 77% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
View performance-per-dollar view →
GB300 NVL72 vs B300: full specs & benchmarks across models →
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:6117.9GB300 NVL72:15002.3 | B300:4759.7GB300 NVL72:9188.2 | B300:2960.8GB300 NVL72:5250.6 |
| Cost ($/M tok) | B300:$0.103GB300 NVL72:$0.043 | B300:$0.132GB300 NVL72:$0.070 | B300:$0.212GB300 NVL72:$0.122 |
| tok/s/MW | B300:3219945GB300 NVL72:7076535 | B300:2505084GB300 NVL72:4334034 | B300:1558336GB300 NVL72:2476691 |
| Concurrency | B300:~13GB300 NVL72:~70 | B300:~6GB300 NVL72:~45 | B300:~3GB300 NVL72:~30 |