X

Xiaomi

MiMo-V2-Pro

MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply optimized for agentic scenarios. It is highly adaptable to general agent frameworks like OpenClaw. It ranks among the global top tier in the standard PinchBench and ClawBench benchmarks, with perceived performance approaching that of Opus 4.6. MiMo-V2-Pro is designed to serve as the brain of agent systems, orchestrating complex workflows, driving production engineering tasks, and delivering results reliably.

Input / 1M tokens
$1.00
Output / 1M tokens
$3.00
Context window
1.0M tokens
Provider
Xiaomi
Cached input / 1M
$0.200

Performance

Median streaming throughput and first-token latency measured by Artificial Analysis.

Output tokens / sec
68 t/s
Time to first token
2.15s

Benchmarks

Intelligence, coding, and math indexes plus the underlying evaluation scores.

Intelligence Index
49
Coding Index
41
Math Index
MMLU-Pro
GPQA
87.0%
HLE
28.3%
LiveCodeBench
SciCode
42.5%
MATH-500
AIME

Benchmarks via Artificial Analysis