MiniMax M3 428B — B200 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) 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 →
B200 / GB300 NVL72 on MiniMax M3 428B at 159 tok/s/user: 34551 / 32568 tok/s/chip, $0.01 / $0.02 per million tokens. B200 is 42% cheaper per token; B200 delivers 6% more tok/s/chip.
Around the middle of the 100–336 tok/s/user interactivity band, at 218 tok/s/user on MiniMax M3 428B: B200 runs 32867 tok/s/chip at $0.01/M tokens, GB300 NVL72 runs 21832 at $0.03/M. B200 is 101% cheaper per token; B200 delivers 51% more tok/s/chip.
Setting 277 tok/s/user as the target on MiniMax M3 428B, B200 produces 29643 tok/s/chip ($0.02 per million tokens) and GB300 NVL72 produces 13103 ($0.05). B200 is 202% cheaper per token; B200 delivers 126% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B200:34551.0GB300 NVL72:32567.6 | B200:32867.1GB300 NVL72:21832.5 | B200:29642.6GB300 NVL72:13103.4 |
| Cost ($/M tok) | B200:$0.014GB300 NVL72:$0.020 | B200:$0.015GB300 NVL72:$0.029 | B200:$0.016GB300 NVL72:$0.049 |
| tok/s/MW | B200:20205266GB300 NVL72:15362054 | B200:19220530GB300 NVL72:10298334 | B200:17334863GB300 NVL72:6180856 |
| Concurrency | B200:~21GB300 NVL72:~29 | B200:~20GB300 NVL72:~20 | B200:~20GB300 NVL72:~24 |