MiniMax M3.1 Flash 428B · Chip comparison

MiniMax M3.1 Flash 428B — B200 vs H100

Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and H100 (NVIDIA Hopper) 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 56–288 tok/s/user interactivity band, at 113 tok/s/user on MiniMax M3.1 Flash 428B: B200 runs 85,201 tok/s/chip at $0.006 per million tokens, H100 runs 5,360 at $0.061. B200 is 91% cheaper per token; B200 delivers 16× the tok/s/chip.

Setting 172 tok/s/user as the target on MiniMax M3.1 Flash 428B, B200 produces 76,115 tok/s/chip ($0.006 per million tokens) and H100 produces 4,131 ($0.079). B200 is 92% cheaper per token; B200 delivers 18× the tok/s/chip.

At 230 tok/s/user interactivity on MiniMax M3.1 Flash 428B, B200 delivers 48,675 tok/s/chip at $0.010 per million tokens; H100 delivers 3,027 tok/s/chip at $0.11. B200 is 91% cheaper per token; B200 delivers 16× the 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.)

View performance per dollar →

B200 vs H100: 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)
B20085,201H1005,360
B20076,115H1004,131
B20048,675H1003,027
Cost ($/M tok)
B200$0.006H100$0.061
B200$0.006H100$0.079
B200$0.010H100$0.11
tok/s/MW
B20049,824,873H1003,912,154
B20044,511,642H1003,015,661
B20028,464,732H1002,209,465
Concurrency
B200~53H100~8
B200~45H100~6
B200~25H100~3