GLM 5/5.1 · Chip comparison
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 1,756 tok/s/chip, MI355X hits 1,369. Costs per million tokens land at $0.27 and $0.30 respectively. B200 is 10% cheaper per token; B200 delivers 28% more tok/s/chip.
B200 / MI355X on GLM 5/5.1 at 51 tok/s/user: 1,287 / 957 tok/s/chip, $0.37 / $0.44 per million tokens. B200 is 14% cheaper per token; B200 delivers 35% more tok/s/chip.
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 1,004 tok/s/chip at $0.48 per million tokens, MI355X runs 709 at $0.59. B200 is 18% cheaper per token; B200 delivers 41% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B2001,756MI355X1,369 | B2001,287MI355X957 | B2001,004MI355X709 |
| Cost ($/M tok) | B200$0.27MI355X$0.30 | B200$0.37MI355X$0.44 | B200$0.48MI355X$0.59 |
| tok/s/MW | B2001,027,090MI355X654,793 | B200752,761MI355X457,666 | B200586,911MI355X339,417 |
| Concurrency | B200~240MI355X~19 | B200~23MI355X~9 | B200~13MI355X~4 |