Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and GB200 NVL72 (NVIDIA Blackwell) on GLM 5.3 744B. 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 →
B300 / GB200 NVL72 on GLM 5.3 744B at 137 tok/s/user: 11622 / 12883 tok/s/chip, $0.05 / $0.04 per million tokens. GB200 NVL72 is 35% cheaper per token; GB200 NVL72 delivers 11% more tok/s/chip.
Around the middle of the 92–273 tok/s/user interactivity band, at 182 tok/s/user on GLM 5.3 744B: B300 runs 7303 tok/s/chip at $0.09/M tokens, GB200 NVL72 runs 9703 at $0.05/M. GB200 NVL72 is 61% cheaper per token; GB200 NVL72 delivers 33% more tok/s/chip.
Setting 228 tok/s/user as the target on GLM 5.3 744B, B300 produces 5206 tok/s/chip ($0.12 per million tokens) and GB200 NVL72 produces 5652 ($0.09). GB200 NVL72 is 32% cheaper per token; GB200 NVL72 delivers 9% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:11622.0GB200 NVL72:12882.7 | B300:7303.0GB200 NVL72:9703.1 | B300:5205.7GB200 NVL72:5652.2 |
| Cost ($/M tok) | B300:$0.054GB200 NVL72:$0.040 | B300:$0.086GB200 NVL72:$0.053 | B300:$0.121GB200 NVL72:$0.091 |
| tok/s/MW | B300:6116829GB200 NVL72:6889127 | B300:3843703GB200 NVL72:5188833 | B300:2739867GB200 NVL72:3022558 |
| Concurrency | B300:~15GB200 NVL72:~69 | B300:~10GB200 NVL72:~46 | B300:~6GB200 NVL72:~6 |
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.
