MiniMax M3 428B — B300 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of B300 (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 →
Throughput at 159 tok/s/user on MiniMax M3 428B: B300 hits 42296 tok/s/chip, GB300 NVL72 hits 32568. Per-million costs land at $0.01 and $0.02 respectively. B300 is 33% cheaper per token; B300 delivers 30% more tok/s/chip.
B300 / GB300 NVL72 on MiniMax M3 428B at 218 tok/s/user: 21684 / 21832 tok/s/chip, $0.03 / $0.03 per million tokens. B300 is 2% cheaper per token; throughput per chip is essentially tied.
Toward the upper edge of the 100–336 tok/s/user interactivity band, at 277 tok/s/user on MiniMax M3 428B: B300 runs 9698 tok/s/chip at $0.06/M tokens, GB300 NVL72 runs 13103 at $0.05/M. GB300 NVL72 is 32% cheaper per token; GB300 NVL72 delivers 35% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
View performance-per-dollar view →
GB300 NVL72 vs B300: full specs & benchmarks across models →
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:42296.2GB300 NVL72:32567.6 | B300:21683.6GB300 NVL72:21832.5 | B300:9698.0GB300 NVL72:13103.4 |
| Cost ($/M tok) | B300:$0.015GB300 NVL72:$0.020 | B300:$0.029GB300 NVL72:$0.029 | B300:$0.065GB300 NVL72:$0.049 |
| tok/s/MW | B300:22261151GB300 NVL72:15362054 | B300:11412438GB300 NVL72:10298334 | B300:5104221GB300 NVL72:6180856 |
| Concurrency | B300:~25GB300 NVL72:~29 | B300:~14GB300 NVL72:~20 | B300:~5GB300 NVL72:~24 |