Head-to-head AI inference benchmark comparison of B300 (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 →
Near the low end of the 126–157 tok/s/user interactivity band, at 133 tok/s/user on GLM 5.3 744B: B300 runs 11884 tok/s/chip at $0.05/M tokens, MI355X runs 2764 at $0.15/M. B300 is 185% cheaper per token; B300 delivers 330% more tok/s/chip.
Setting 142 tok/s/user as the target on GLM 5.3 744B, B300 produces 10471 tok/s/chip ($0.06 per million tokens) and MI355X produces 1858 ($0.22). B300 is 274% cheaper per token; B300 delivers 463% more tok/s/chip.
At 150 tok/s/user interactivity on GLM 5.3 744B, B300 delivers 9342 tok/s/chip at $0.07 per million tokens; MI355X delivers 1751 tok/s/chip at $0.24. B300 is 254% cheaper per token; B300 delivers 434% more tok/s/chip at this point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:11883.5MI355X:2763.7 | B300:10471.4MI355X:1858.3 | B300:9341.5MI355X:1750.8 |
| Cost ($/M tok) | B300:$0.053MI355X:$0.151 | B300:$0.060MI355X:$0.224 | B300:$0.067MI355X:$0.238 |
| tok/s/MW | B300:6254481MI355X:1322360 | B300:5511250MI355X:889126 | B300:4916580MI355X:837691 |
| Concurrency | B300:~16MI355X:~2 | B300:~15MI355X:~2 | B300:~14MI355X:~2 |
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.
