gpt-oss 120B · Chip comparison

gpt-oss 120B — GB200 NVL72 vs MI355X

Head-to-head AI inference benchmark comparison of GB200 NVL72 (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.

Near the low end of the 68–305 tok/s/user interactivity band, at 127 tok/s/user on gpt-oss 120B: GB200 NVL72 runs 39,042 tok/s/chip at $0.013 per million tokens, MI355X runs 19,134 at $0.022. GB200 NVL72 is 39% cheaper per token; GB200 NVL72 delivers 104% more tok/s/chip.

Setting 187 tok/s/user as the target on gpt-oss 120B, GB200 NVL72 produces 28,526 tok/s/chip ($0.018 per million tokens) and MI355X produces 11,474 ($0.036). GB200 NVL72 is 50% cheaper per token; GB200 NVL72 delivers 149% more tok/s/chip.

At 246 tok/s/user interactivity on gpt-oss 120B, GB200 NVL72 delivers 18,958 tok/s/chip at $0.027 per million tokens; MI355X delivers 3,618 tok/s/chip at $0.12. GB200 NVL72 is 76% cheaper per token; GB200 NVL72 delivers 5.2× the tok/s/chip at this point. (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.)

View performance per dollar →

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)
GB200 NVL7239,042MI355X19,134
GB200 NVL7228,526MI355X11,474
GB200 NVL7218,958MI355X3,618
Cost ($/M tok)
GB200 NVL72$0.013MI355X$0.022
GB200 NVL72$0.018MI355X$0.036
GB200 NVL72$0.027MI355X$0.12
tok/s/MW
GB200 NVL7220,878,221MI355X9,154,931
GB200 NVL7215,254,396MI355X5,490,178
GB200 NVL7210,137,992MI355X1,731,095
Concurrency
GB200 NVL72~489MI355X~18
GB200 NVL72~109MI355X~7
GB200 NVL72~53MI355X~16