gpt-oss 120B · Chip comparison
gpt-oss 120B — B200 vs MI355X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on gpt-oss 120B. 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 104 tok/s/user on gpt-oss 120B: B200 hits 32,860 tok/s/chip, MI355X hits 23,358. Costs per million tokens land at $0.015 and $0.018 respectively. B200 is 18% cheaper per token; B200 delivers 41% more tok/s/chip.
B200 / MI355X on gpt-oss 120B at 171 tok/s/user: 20,448 / 13,182 tok/s/chip, $0.024 / $0.032 per million tokens. B200 is 26% cheaper per token; B200 delivers 55% more tok/s/chip.
Toward the upper edge of the 38–305 tok/s/user interactivity band, at 238 tok/s/user on gpt-oss 120B: B200 runs 13,725 tok/s/chip at $0.035 per million tokens, MI355X runs 3,911 at $0.11. B200 is 67% cheaper per token; B200 delivers 3.5× the tok/s/chip. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B20032,860MI355X23,358 | B20020,448MI355X13,182 | B20013,725MI355X3,911 |
| Cost ($/M tok) | B200$0.015MI355X$0.018 | B200$0.024MI355X$0.032 | B200$0.035MI355X$0.11 |
| tok/s/MW | B20019,216,342MI355X11,176,178 | B20011,958,138MI355X6,307,067 | B2008,026,222MI355X1,871,375 |
| Concurrency | B200~33MI355X~26 | B200~30MI355X~9 | B200~6MI355X~16 |