GLM 5/5.1 — B200 vs MI355X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) 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 32 tok/s/user on GLM 5/5.1: B200 hits 1756 tok/s/GPU, MI355X hits 1369. Per-million costs land at $0.31 and $0.30 respectively. MI355X is 1% cheaper per token; B200 delivers 28% more tok/s/GPU.
B200 / MI355X on GLM 5/5.1 at 51 tok/s/user: 1287 / 957 tok/s/GPU, $0.42 / $0.43 per million tokens. B200 is 2% cheaper per token; B200 delivers 35% more tok/s/GPU.
Toward the upper edge of the 12–90 tok/s/user interactivity band, at 71 tok/s/user on GLM 5/5.1: B200 runs 1004 tok/s/GPU at $0.54/M tokens, MI355X runs 709 at $0.57/M. B200 is 6% cheaper per token; B200 delivers 41% more tok/s/GPU. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:1756.3MI355X:1368.5 | B200:1287.2MI355X:956.5 | B200:1003.6MI355X:709.4 |
| Cost ($/M tok) | B200:$0.309MI355X:$0.305 | B200:$0.417MI355X:$0.427 | B200:$0.542MI355X:$0.572 |
| tok/s/MW | B200:809366MI355X:516422 | B200:593190MI355X:360952 | B200:462497MI355X:267691 |
| Concurrency | B200:~240MI355X:~19 | B200:~23MI355X:~9 | B200:~13MI355X:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.