Models Model details

Xiaomi

Xiaomi: MiMo-V2.5-Pro

xiaomi/mimo-v2.5-pro

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. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.

Input
$0.435

/ 1M tokens

Output
$0.87

/ 1M tokens

Context window
1.05M

tokens

Limits

Context

1,050,000

tokens

Max output

131,072

12% of the context window

Parameters

1,023,182,841,600

Model facts

Author

Xiaomi

Tokenizer

Other

Modality

Text -> Text

License

MIT

Created

Apr 22, 2026

Hugging Face

XiaomiMiMo/MiMo-V2.5-Pro

Default generation parameters

temperature

1

top_p

0.95

Publication status

Hugging Face: verifiedLicense: publishedParameter count: published

Modalities

Input · TextOutput · Text

Generation controls

Frequency penaltyInclude reasoningLogprobsMax tokensPresence penaltyReasoningRepetition penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop kTop logprobsTop p

Capability scores

21.3
Agentic index

Better than 53% of models compared

60.2
Coding index

Better than 65% of models compared

26
Intelligence index

Better than 65% of models compared

Creative tasks

Category performance

3D
Top 32%

1245 Elo

53.6% win

Games
Top 32%

1262 Elo

53.1% win

Code
Top 30%

1267 Elo

51.5% win

UI components
Top 39%

1249 Elo

50.8% win

Websites
Top 27%

1268 Elo

50.8% win

Data visualization
Top 32%

1258 Elo

50.5% win

SVG
Top 49%

1179 Elo

48.0% win

ASCII art
Top 60%

1157 Elo

46.0% win