GLM 5.3 744B · Chip comparison

GLM 5.3 744B — H200 vs Vera Rubin NVL72

Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) and Vera Rubin NVL72 (NVIDIA Vera Rubin) 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 →

At 416 tok/s/user on GLM 5.3 744B, Vera Rubin NVL72 delivers 27,636 tok/s/chip at $0.036 per million tokens; H200 hasn't been benchmarked at this target.

Vera Rubin NVL72 hits 12,918 tok/s/chip for $0.078 per million tokens at 628 tok/s/user on GLM 5.3 744B. No H200 data at this operating point.

Vera Rubin NVL72: 6,657 tok/s/chip, $0.15 per million tokens at 840 tok/s/user on GLM 5.3 744B. H200 is unmeasured here. (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 →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.

Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Throughput (tok/s/chip)
H200—Vera Rubin NVL7227,636
H200—Vera Rubin NVL7212,918
H200—Vera Rubin NVL726,657
Cost ($/M tok)
H200—Vera Rubin NVL72$0.036
H200—Vera Rubin NVL72$0.078
H200—Vera Rubin NVL72$0.15
tok/s/MW
H200—Vera Rubin NVL728,374,424
H200—Vera Rubin NVL723,914,513
H200—Vera Rubin NVL722,017,413
Concurrency
H200—Vera Rubin NVL72~56
H200—Vera Rubin NVL72~49
H200—Vera Rubin NVL72~24