Kimi K3.1 Pro — B300 vs MI355X
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on Kimi K3.1 Pro. 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 63 tok/s/user as the target on Kimi K3.1 Pro, B300 produces 8432 tok/s/chip ($0.07 per million tokens) and MI355X produces 9127 ($0.05). MI355X is 63% cheaper per token; MI355X delivers 8% more tok/s/chip.
At 101 tok/s/user interactivity on Kimi K3.1 Pro, B300 delivers 6301 tok/s/chip at $0.10 per million tokens; MI355X delivers 4222 tok/s/chip at $0.10. Cost per token is essentially tied; B300 delivers 49% more tok/s/chip at this point.
B300 posts 5098 tok/s/chip for $0.12 per million tokens at 138 tok/s/user on Kimi K3.1 Pro; MI355X posts 2743 tok/s/chip for $0.15. B300 is 23% cheaper per token; B300 delivers 86% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:8431.8MI355X:9127.3 | B300:6300.6MI355X:4222.3 | B300:5097.8MI355X:2743.1 |
| Cost ($/M tok) | B300:$0.074MI355X:$0.046 | B300:$0.100MI355X:$0.099 | B300:$0.123MI355X:$0.152 |
| tok/s/MW | B300:4437778MI355X:4367151 | B300:3316119MI355X:2020232 | B300:2683027MI355X:1312508 |
| Concurrency | B300:~16MI355X:~16 | B300:~15MI355X:~6 | B300:~7MI355X:~3 |