Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on GLM 5.3 744B. 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 →
Setting 126 tok/s/user as the target on GLM 5.3 744B, B200 produces 9273 tok/s/chip ($0.05 per million tokens) and MI355X produces 4897 ($0.09). B200 is 64% cheaper per token; B200 delivers 89% more tok/s/chip.
At 156 tok/s/user interactivity on GLM 5.3 744B, B200 delivers 7846 tok/s/chip at $0.06 per million tokens; MI355X delivers 3733 tok/s/chip at $0.11. B200 is 82% cheaper per token; B200 delivers 110% more tok/s/chip at this point.
B200 posts 7223 tok/s/chip for $0.07 per million tokens at 186 tok/s/user on GLM 5.3 744B; MI355X posts 2683 tok/s/chip for $0.16. B200 is 133% cheaper per token; B200 delivers 169% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:9273.2MI355X:4897.4 | B200:7846.0MI355X:3732.6 | B200:7223.2MI355X:2683.0 |
| Cost ($/M tok) | B200:$0.052MI355X:$0.085 | B200:$0.061MI355X:$0.112 | B200:$0.067MI355X:$0.155 |
| tok/s/MW | B200:5422909MI355X:2343233 | B200:4588323MI355X:1785921 | B200:4224079MI355X:1283708 |
| Concurrency | B200:~14MI355X:~3 | B200:~11MI355X:~2 | B200:~9MI355X:~4 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.
