Qwen 3.5 397B-A17B · Chip comparison

Qwen 3.5 397B-A17B — B200 vs H100

Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and H100 (NVIDIA Hopper) on Qwen 3.5 397B-A17B. 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 71 tok/s/user interactivity on Qwen 3.5 397B-A17B, B200 delivers 37,458 tok/s/chip at $0.013 per million tokens; H100 delivers 6,053 tok/s/chip at $0.054. B200 is 76% cheaper per token; B200 delivers 6.2× the tok/s/chip at this point.

B200 posts 33,310 tok/s/chip for $0.014 per million tokens at 123 tok/s/user on Qwen 3.5 397B-A17B; H100 posts 3,578 tok/s/chip for $0.091. B200 is 84% cheaper per token; B200 delivers 9.3× the tok/s/chip.

Throughput at 176 tok/s/user on Qwen 3.5 397B-A17B: B200 hits 21,401 tok/s/chip, H100 hits 2,528. Costs per million tokens land at $0.022 and $0.13 respectively. B200 is 83% cheaper per token; B200 delivers 8.5× the tok/s/chip. (Numbers reflect the default agentic-traces · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)

View performance per dollar →

B200 vs H100: full specs & benchmarks across models →

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)
B20037,458H1006,053
B20033,310H1003,578
B20021,401H1002,528
Cost ($/M tok)
B200$0.013H100$0.054
B200$0.014H100$0.091
B200$0.022H100$0.13
tok/s/MW
B20021,904,983H1004,418,126
B20019,479,812H1002,611,475
B20012,514,953H1001,844,968
Concurrency
B200~30H100~12
B200~23H100~6
B200~14H100~4