Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and H200 (NVIDIA Hopper) 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 →
B200: 8178 tok/s/chip, $0.06 per million tokens at 147 tok/s/user on GLM 5.3 744B. H200 is unmeasured here.
At 198 tok/s/user on GLM 5.3 744B, B200 delivers 6883 tok/s/chip at $0.07 per million tokens; H200 hasn't been benchmarked at this target.
B200 hits 4320 tok/s/chip for $0.11 per million tokens at 250 tok/s/user on GLM 5.3 744B. No H200 data at this operating point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:8178.4H200:— | B200:6883.3H200:— | B200:4319.5H200:— |
| Cost ($/M tok) | B200:$0.059H200:— | B200:$0.070H200:— | B200:$0.111H200:— |
| tok/s/MW | B200:4782714H200:— | B200:4025345H200:— | B200:2526033H200:— |
| Concurrency | B200:~12H200:— | B200:~8H200:— | B200:~5H200:— |
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.
