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
Phi-4-mini
Open
Share
Add to comparison
Tool use
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#170
46.4 points · 180 models
Open-weight rank
#100
50.1 points · 109 models
Data coverage
22 items
1 source · updated through 2025-05-14
Domain performance
Coding
#139 / 160
59.8
Research
#163 / 174
55.9
Agents
#122 / 125
49.7
Evaluation highlights
All evaluations
MMLU-Redux
Reasoning · Qwen3 Technical Report
67.9%
86
/ 102
LiveCodeBench v5
Coding · Qwen3 Technical Report
10.4%
33
/ 36
BFCL v3 Full
Agents · Qwen3 Technical Report
31.3%
46
/ 49
Arena-Hard
Conversation · Qwen3 Technical Report
32.8%
32
/ 39
MultiIF
Multilingual · Qwen3 Technical Report
40.5%
37
/ 45
IFEval strict prompt
Instruction following · Qwen3 Technical Report
68.6%
47
/ 55
Basic information
Context (input / output)
131K / 4K
Parameters
3.8B
Release date
2025-02
License
MIT
Input modalities
Text
Output modalities
Text
Availability
vLLM · BF16
Deployment options
BF16 · 10 GB VRAM
Related links
Official site
HuggingFace