GLM 5/5.1 — B200 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) on GLM 5/5.1. 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.
Throughput at 47 tok/s/user on GLM 5/5.1: B200 hits 1360 tok/s/chip, GB300 NVL72 hits 6056. Per-million costs land at $0.35 and $0.11 respectively. GB300 NVL72 is 234% cheaper per token; GB300 NVL72 delivers 345% more tok/s/chip.
B200 / GB300 NVL72 on GLM 5/5.1 at 67 tok/s/user: 1062 / 1809 tok/s/chip, $0.45 / $0.35 per million tokens. GB300 NVL72 is 28% cheaper per token; GB300 NVL72 delivers 70% more tok/s/chip.
Toward the upper edge of the 26–108 tok/s/user interactivity band, at 88 tok/s/user on GLM 5/5.1: B200 runs 780 tok/s/chip at $0.62/M tokens, GB300 NVL72 runs 526 at $1.22/M. B200 is 98% cheaper per token; B200 delivers 48% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:1359.7GB300 NVL72:6056.0 | B200:1062.4GB300 NVL72:1808.8 | B200:780.1GB300 NVL72:526.4 |
| Cost ($/M tok) | B200:$0.353GB300 NVL72:$0.106 | B200:$0.452GB300 NVL72:$0.355 | B200:$0.616GB300 NVL72:$1.219 |
| tok/s/MW | B200:795154GB300 NVL72:2856617 | B200:621264GB300 NVL72:853218 | B200:456183GB300 NVL72:248323 |
| Concurrency | B200:~27GB300 NVL72:~1958 | B200:~15GB300 NVL72:~359 | B200:~9GB300 NVL72:~135 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Total Tokens per $1 USD (Owning - Hyperscaler) vs. Interactivity
GLM5/5.1 744B • FP4 • 8K / 1K • Source: SemiAnalysis InferenceX™
TCO $/chip/hr: H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
No data available
Please change the model, sequence, precision, date range or chip selection.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip