GLM 5.3 744B — B300 vs MI325X Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) on GLM 5.3 744B. Large-hyperscaler-volume ownership TCO normalized by total tokens — performance per dollar across LLM workloads. Pick the more cost-efficient SKU at every target interactivity level. 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 →
At 61 tok/s/user on GLM 5.3 744B, B300 costs $0.06 per million tokens; MI325X costs $0.44. B300 is 694% more cost-efficient at this operating point.
B300 edges MI325X at 120 tok/s/user on GLM 5.3 744B — $0.08 per million tokens versus $0.44, a 486% cost-per-token gap.
Push GLM 5.3 744B to 179 tok/s/user and B300 lands at $0.14 per million tokens against MI325X's $0.44 — B300 pulls ahead by 222%. (Numbers reflect the default agentic-traces · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): B300 $2.26/chip/hr · MI325X $1.10/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.056MI325X:$0.444 | B300:$0.076MI325X:$0.444 | B300:$0.138MI325X:$0.444 |
| Concurrency | B300:~16MI325X:~1 | B300:~13MI325X:~1 | B300:~6MI325X:~1 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No data available
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.