Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and H100 (NVIDIA Hopper) on Muse Spark Open 816B. 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
B300 posts 21347 tok/s/chip for $0.03 per million tokens at 52 tok/s/user on Muse Spark Open 816B; H100 posts 1316 tok/s/chip for $0.25. B300 is 740% cheaper per token; B300 delivers 1522% more tok/s/chip.
Throughput at 91 tok/s/user on Muse Spark Open 816B: B300 hits 21347 tok/s/chip, H100 hits 1316. Per-million costs land at $0.03 and $0.25 respectively. B300 is 740% cheaper per token; B300 delivers 1522% more tok/s/chip.
B300 / H100 on Muse Spark Open 816B at 129 tok/s/user: 19664 / 1316 tok/s/chip, $0.03 / $0.25 per million tokens. B300 is 674% cheaper per token; B300 delivers 1394% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:21346.8H100:1315.8 | B300:21346.8H100:1315.8 | B300:19663.5H100:1315.8 |
| Cost ($/M tok) | B300:$0.029H100:$0.247 | B300:$0.029H100:$0.247 | B300:$0.032H100:$0.247 |
| tok/s/MW | B300:11235170H100:960474 | B300:11235170H100:960474 | B300:10349222H100:960474 |
| Concurrency | B300:~16H100:~1 | B300:~16H100:~1 | B300:~15H100:~1 |
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.
