About
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....
Related Models
Pricing
Input
$0.43
per 1M tokens
Output
$0.87
per 1M tokens
Blended
$0.54
per 1M tokens
Cheaper than 50% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.54
Monthly
$16.31
vs. Similar Models
OpenAI: GPT-5.2Q:0.0
$4.81+785%
MoonshotAI: Kimi K2.7 CodeQ:-0.3
$1.43+163%
Claude Opus 4.7 (Non-reasoning, High Effort)Q:+0.5
$10.00+1739%
MoonshotAI: Kimi K2.6Q:+0.6
$1.35+148%
Performance
46
tokens/sec
Faster than 12% of models
1.99
seconds
Faster than 22% of models
45.08
seconds
Faster than 8% of models
Market Median
94 tok/s
51% slower
Median TTFT
1.11s
79% slower
Throughput/Dollar
85
tok/s per $/1M
Speed Comparison
Microsoft: Phi 4 Mini Instruct
47 tok/s+0%
Llama 3 Instruct 70B
47 tok/s+1%
Grok 4
47 tok/s+1%
Context Window
1.0M
tokens
Larger than 90% of models
Max Output
131K
tokens
13% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
86.6%
HLE
33.8%
LiveCodeBenchNot evaluated
SciCode
50.2%
TerminalBench Hard
43.2%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
79.9%
Long Context Recall
73.3%
Tau2
94.2%
Market AverageTop Score