Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) on Kimi K3 2.8T. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics β 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 β
Near the low end of the 19β192 tok/s/user interactivity band, at 62 tok/s/user on Kimi K3 2.8T: B200 runs 4964 tok/s/chip at $0.10/M tokens, GB300 NVL72 runs 13289 at $0.05/M. GB300 NVL72 is 101% cheaper per token; GB300 NVL72 delivers 168% more tok/s/chip.
Setting 105 tok/s/user as the target on Kimi K3 2.8T, B200 produces 2792 tok/s/chip ($0.17 per million tokens) and GB300 NVL72 produces 9326 ($0.07). GB300 NVL72 is 150% cheaper per token; GB300 NVL72 delivers 234% more tok/s/chip.
At 149 tok/s/user interactivity on Kimi K3 2.8T, B200 delivers 1683 tok/s/chip at $0.29 per million tokens; GB300 NVL72 delivers 6554 tok/s/chip at $0.10. GB300 NVL72 is 192% cheaper per token; GB300 NVL72 delivers 289% more tok/s/chip at this point. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:4963.7GB300 NVL72:13289.1 | B200:2792.1GB300 NVL72:9326.4 | B200:1683.2GB300 NVL72:6553.6 |
| Cost ($/M tok) | B200:$0.097GB300 NVL72:$0.048 | B200:$0.172GB300 NVL72:$0.069 | B200:$0.286GB300 NVL72:$0.098 |
| tok/s/MW | B200:2902730GB300 NVL72:6268425 | B200:1632807GB300 NVL72:4399256 | B200:984301GB300 NVL72:3091336 |
| Concurrency | B200:~16GB300 NVL72:~49 | B200:~8GB300 NVL72:~48 | B200:~4GB300 NVL72:~34 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.
