Head-to-head AI inference benchmark comparison of B200 (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
B200 / MI355X on Qwen 3.8 Flash Next 176B-A6B at 86 tok/s/user: 61888 / 58839 tok/s/chip, $0.01 / $0.01 per million tokens. MI355X is 10% cheaper per token; B200 delivers 5% more tok/s/chip.
Around the middle of the 67β145 tok/s/user interactivity band, at 106 tok/s/user on Qwen 3.8 Flash Next 176B-A6B: B200 runs 55675 tok/s/chip at $0.01/M tokens, MI355X runs 36602 at $0.01/M. B200 is 32% cheaper per token; B200 delivers 52% more tok/s/chip.
Setting 125 tok/s/user as the target on Qwen 3.8 Flash Next 176B-A6B, B200 produces 48975 tok/s/chip ($0.01 per million tokens) and MI355X produces 19807 ($0.02). B200 is 114% cheaper per token; B200 delivers 147% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:61887.7MI355X:58838.9 | B200:55675.0MI355X:36602.3 | B200:48974.9MI355X:19807.3 |
| Cost ($/M tok) | B200:$0.008MI355X:$0.007 | B200:$0.009MI355X:$0.011 | B200:$0.010MI355X:$0.021 |
| tok/s/MW | B200:36191645MI355X:28152565 | B200:32558493MI355X:17513060 | B200:28640286MI355X:9477154 |
| Concurrency | B200:~14MI355X:~13 | B200:~12MI355X:~8 | B200:~10MI355X:~5 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
