Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
MiMo-V2.5 Base
Open
Share
Add to comparison
Overview
Evaluations
Evaluation overview
Overall rank
#147
60.9 points · 201 models
Open-weight rank
#71
63.4 points · 119 models
Data coverage
20 items
1 source · updated through 2026-04-27
Domain performance
Coding
#128 / 181
62
Research
#142 / 195
69.9
Evaluation highlights
All evaluations
MATH
Reasoning · MiMo-V2.5-Pro Technical Report
67.7%
4
/ 30
SWE-Bench (AgentLess)
Coding · MiMo-V2.5-Pro Technical Report
30.8%
2
/ 3
C-Eval
Chinese · MiMo-V2.5-Pro Technical Report
88.6%
20
/ 64
GlobalMMLU
Multilingual · MiMo-V2.5-Pro Technical Report
77.4%
3
/ 3
BBH
Reasoning · MiMo-V2.5-Pro Technical Report
87.2%
6
/ 30
MMLU-Redux
Reasoning · MiMo-V2.5-Pro Technical Report
89.8%
37
/ 102
Basic information
Context (input / output)
262K / -
Parameters
310B / 15B active
Release date
2026-04
License
MIT
Input modalities
Text · Image · Video · Audio
Output modalities
Text
Architecture
Sparse MoE
Total parameters
310B
Related links
Official site
HuggingFace
ModelScope
Version relationships
Mimo-V2.5 family
MiMo-V2.5
2026-04 · Same series
MiMo-V2.5 Base
Current
2026-04 · Current model