Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on Qwen 3.8 Flash Next 176B-A6B. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics β 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 β
Throughput at 86 tok/s/user on Qwen 3.8 Flash Next 176B-A6B: B300 hits 80846 tok/s/chip, MI355X hits 58839. Per-million costs land at $0.01 and $0.01 respectively. MI355X is 10% cheaper per token; B300 delivers 37% more tok/s/chip.
B300 / MI355X on Qwen 3.8 Flash Next 176B-A6B at 106 tok/s/user: 67218 / 36602 tok/s/chip, $0.01 / $0.01 per million tokens. B300 is 22% cheaper per token; B300 delivers 84% more tok/s/chip.
Toward the upper edge of the 67β145 tok/s/user interactivity band, at 125 tok/s/user on Qwen 3.8 Flash Next 176B-A6B: B300 runs 55364 tok/s/chip at $0.01/M tokens, MI355X runs 19807 at $0.02/M. B300 is 86% cheaper per token; B300 delivers 180% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:80846.0MI355X:58838.9 | B300:67217.8MI355X:36602.3 | B300:55364.0MI355X:19807.3 |
| Cost ($/M tok) | B300:$0.008MI355X:$0.007 | B300:$0.009MI355X:$0.011 | B300:$0.011MI355X:$0.021 |
| tok/s/MW | B300:42550528MI355X:28152565 | B300:35377769MI355X:17513060 | B300:29138944MI355X:9477154 |
| Concurrency | B300:~16MI355X:~13 | B300:~14MI355X:~8 | B300:~11MI355X:~5 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
