Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on MiniMax M3 428B. 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 66–282 tok/s/user interactivity band, at 120 tok/s/user on MiniMax M3 428B: B300 runs 54988 tok/s/chip at $0.01/M tokens, MI355X runs 22134 at $0.02/M. B300 is 65% cheaper per token; B300 delivers 148% more tok/s/chip.
Setting 174 tok/s/user as the target on MiniMax M3 428B, B300 produces 34343 tok/s/chip ($0.02 per million tokens) and MI355X produces 13989 ($0.03). B300 is 63% cheaper per token; B300 delivers 145% more tok/s/chip.
At 228 tok/s/user interactivity on MiniMax M3 428B, B300 delivers 21571 tok/s/chip at $0.03 per million tokens; MI355X delivers 8935 tok/s/chip at $0.05. B300 is 60% cheaper per token; B300 delivers 141% more tok/s/chip at this point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:54988.2MI355X:22134.3 | B300:34343.3MI355X:13989.5 | B300:21571.4MI355X:8934.6 |
| Cost ($/M tok) | B300:$0.011MI355X:$0.019 | B300:$0.018MI355X:$0.030 | B300:$0.029MI355X:$0.047 |
| tok/s/MW | B300:28941163MI355X:10590566 | B300:18075433MI355X:6693528 | B300:11353350MI355X:4274948 |
| Concurrency | B300:~21MI355X:~16 | B300:~20MI355X:~9 | B300:~14MI355X:~1 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
TCO $/chip/hr:
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
Matching measurements exist, but their chip series are hidden.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip
1 The ATOM engine is promising, however it has yet to serve production tokens. It is still in its infant stage.
MiniMax M3 428B 8K / 1K Total Tokens per $1 TCO vs. Interactivity