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
DeepSeek-V4-Flash Base
Open
Share
Add to comparison
Overview
Evaluations
Evaluation overview
Overall rank
#118
62.4 points · 180 models
Open-weight rank
#53
67.6 points · 109 models
Data coverage
12 items
1 source · updated through 2026-04-27
Domain performance
Research
#111 / 174
72.8
Evaluation highlights
All evaluations
MMLU
Reasoning · MiMo-V2.5-Pro Technical Report
88.7%
7
/ 46
C-Eval
Chinese · MiMo-V2.5-Pro Technical Report
92.1%
9
/ 64
BBH
Reasoning · MiMo-V2.5-Pro Technical Report
86.9%
7
/ 30
GSM8K
Reasoning · MiMo-V2.5-Pro Technical Report
90.8%
11
/ 30
MMLU-Redux
Reasoning · MiMo-V2.5-Pro Technical Report
89.4%
38
/ 102
DROP
Reasoning · MiMo-V2.5-Pro Technical Report
88.6%
6
/ 15
Basic information
Context (input / output)
1M / 393K
Parameters
284B / 13B active
Release date
2026-04
License
MIT
Input modalities
Text
Output modalities
Text
Active parameters
13B
Related links
Official site
HuggingFace
Version relationships
DeepSeek-V4 family
DeepSeek-V4-Flash
2026-04 · Same series
DeepSeek-V4-Flash Base
Current
2026-04 · Current model
DeepSeek-V4-Pro
2026-04 · Same series
DeepSeek-V4-Pro Base
2026-04 · Same series