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
Qwen2.5-7B
Open
Share
Add to comparison
Tool use
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#161
50.3 points · 180 models
Open-weight rank
#91
54.6 points · 109 models
Data coverage
29 items
1 source · updated through 2025-05-14
Domain performance
Coding
#132 / 160
61.2
Research
#156 / 174
59.3
Agents
#109 / 125
54.9
Long context
#81 / 82
43.5
Evaluation highlights
All evaluations
BFCL v3 Full
Agents · Qwen3 Technical Report
55.8%
33
/ 49
RULER 4K
Long context · Qwen3 Technical Report
96.7%
7
/ 10
MATH 500
Reasoning · Qwen3 Technical Report
77.6%
34
/ 44
LiveCodeBench v5
Coding · Qwen3 Technical Report
14.4%
29
/ 36
C-Eval
Chinese · Qwen3 Technical Report
76.2%
42
/ 64
AlignBench v1.1
Conversation · Qwen3 Technical Report
7.27score
25
/ 35
Basic information
Context (input / output)
131K / 8K
Parameters
7.6B
Release date
2024-09
License
Apache 2.0
Input modalities
Text
Output modalities
Text
Availability
Ollama · Q4_K_M
Deployment options
GGUF Q4_K_M · 8 GB VRAM
Related links
Official site
HuggingFace
Version relationships
Qwen2.5-7B family
Qwen2.5-7B
Current
2024-09 · Current model
Qwen2.5-7B
2024-09 · Same series