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
Qwen3-32B
Open
Share
Add to comparison
Tool use · Reasoning
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#96
66.8 points · 180 models
Open-weight rank
#38
73.3 points · 109 models
Data coverage
109 items
2 sources · updated through 2026-07-16
Domain performance
Coding
#85 / 160
68.9
Research
#93 / 174
76.9
Agents
#85 / 125
63.3
Long context
#70 / 82
61
Evaluation highlights
All evaluations
RULER 4K
Long context · Qwen3 Technical Report · Non-reasoning mode
98.4%
1
/ 10
ZebraLogic
Reasoning · Qwen3 Technical Report
88.8%
5
/ 39
LiveCodeBench v5
Coding · Qwen3 Technical Report
65.7%
5
/ 36
BFCL v3 Full
Agents · Qwen3 Technical Report
70.3%
11
/ 49
MLogiQA
Multilingual · Qwen3 Technical Report
76.3%
2
/ 35
Arena-Hard
Conversation · Qwen3 Technical Report
93.8%
3
/ 39
Basic information
Context (input / output)
131K / 33K
Parameters
32.8B
Release date
2025-04
License
Apache 2.0
Input modalities
Text
Output modalities
Text
Availability
vLLM · FP8
Deployment options
FP8 · 39 GB VRAM
Related links
Official site
HuggingFace
Version relationships
Qwen3-32B family
Qwen3-32B
Current
2025-04 · Current model
Qwen3-32B-Base
2025-04 · Same series