Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and GB300 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 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
GB200 NVL72 / GB300 NVL72 on GLM 5.3 744B at 135 tok/s/user: 14234 / 16586 tok/s/chip, $0.04 / $0.04 per million tokens. GB200 NVL72 is 7% cheaper per token; GB300 NVL72 delivers 17% more tok/s/chip.
Around the middle of the 84β291 tok/s/user interactivity band, at 187 tok/s/user on GLM 5.3 744B: GB200 NVL72 runs 9530 tok/s/chip at $0.05/M tokens, GB300 NVL72 runs 8232 at $0.08/M. GB200 NVL72 is 44% cheaper per token; GB200 NVL72 delivers 16% more tok/s/chip.
Setting 240 tok/s/user as the target on GLM 5.3 744B, GB200 NVL72 produces 5081 tok/s/chip ($0.10 per million tokens) and GB300 NVL72 produces 4925 ($0.13). GB200 NVL72 is 28% cheaper per token; GB200 NVL72 delivers 3% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL72:14233.6GB300 NVL72:16585.8 | GB200 NVL72:9529.8GB300 NVL72:8232.1 | GB200 NVL72:5080.5GB300 NVL72:4925.3 |
| Cost ($/M tok) | GB200 NVL72:$0.036GB300 NVL72:$0.039 | GB200 NVL72:$0.054GB300 NVL72:$0.078 | GB200 NVL72:$0.102GB300 NVL72:$0.130 |
| tok/s/MW | GB200 NVL72:7611527GB300 NVL72:7823510 | GB200 NVL72:5096165GB300 NVL72:3883086 | GB200 NVL72:2716857GB300 NVL72:2323250 |
| Concurrency | GB200 NVL72:~76GB300 NVL72:~48 | GB200 NVL72:~46GB300 NVL72:~45 | GB200 NVL72:~5GB300 NVL72:~9 |
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.
