MiniMax M3.1 Flash 428B · Chip comparison
MiniMax M3.1 Flash 428B — GB200 NVL72 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) on MiniMax M3.1 Flash 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 18–649 tok/s/user interactivity band, at 176 tok/s/user on MiniMax M3.1 Flash 428B: GB200 NVL72 runs 98,848 tok/s/chip at $0.005 per million tokens, GB300 NVL72 runs 126,837 at $0.005. GB300 NVL72 is 3% cheaper per token; GB300 NVL72 delivers 28% more tok/s/chip.
Setting 333 tok/s/user as the target on MiniMax M3.1 Flash 428B, GB200 NVL72 produces 26,334 tok/s/chip ($0.020 per million tokens) and GB300 NVL72 produces 28,215 ($0.023). GB200 NVL72 is 14% cheaper per token; GB300 NVL72 delivers 7% more tok/s/chip.
At 491 tok/s/user interactivity on MiniMax M3.1 Flash 428B, GB200 NVL72 delivers 9,827 tok/s/chip at $0.053 per million tokens; GB300 NVL72 delivers 9,525 tok/s/chip at $0.067. GB200 NVL72 is 22% cheaper per token; GB200 NVL72 delivers 3% more tok/s/chip at this point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GB300 NVL72 vs GB200 NVL72: full specs & benchmarks across models →
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL7298,848GB300 NVL72126,837 | GB200 NVL7226,334GB300 NVL7228,215 | GB200 NVL729,827GB300 NVL729,525 |
| Cost ($/M tok) | GB200 NVL72$0.005GB300 NVL72$0.005 | GB200 NVL72$0.020GB300 NVL72$0.023 | GB200 NVL72$0.053GB300 NVL72$0.067 |
| tok/s/MW | GB200 NVL7252,859,865GB300 NVL7259,828,782 | GB200 NVL7214,082,219GB300 NVL7213,308,965 | GB200 NVL725,255,114GB300 NVL724,493,084 |
| Concurrency | GB200 NVL72~256GB300 NVL72~886 | GB200 NVL72~14GB300 NVL72~16 | GB200 NVL72~4GB300 NVL72~4 |