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
Qwen3.5-2B
Open
Share
Add to comparison
Tool use
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#144
55.9 points · 180 models
Open-weight rank
#75
61.3 points · 109 models
Data coverage
22 items
1 source · updated through 2026-03-01
Domain performance
Research
#139 / 174
65.9
Agents
#84 / 125
63.3
Vision
#58 / 65
66.2
Long context
#64 / 82
64.6
Evaluation highlights
All evaluations
Global PIQA
Reasoning · Qwen3.5-2B Technical Report
69.3%
1
/ 2
τ²-Bench
Agents · Qwen3.5-2B Technical Report
48.8%
17
/ 21
LongBench v2
Long context · Qwen3.5-2B Technical Report
38.7%
18
/ 22
MMMU
Multimodal · Qwen3.5-2B Technical Report
63.1%
22
/ 25
IFEval
Instruction following · Qwen3.5-2B Technical Report
78.6%
27
/ 30
PolyMath
Multilingual · Qwen3.5-2B Technical Report
26.1%
21
/ 44
Basic information
Context (input / output)
262K / 8K
Parameters
2B
Release date
2026-02
License
Apache 2.0
Input modalities
Text · Image
Output modalities
Text
Availability
vLLM · BF16
Deployment options
BF16 · 5 GB VRAM
Related links
Official site
HuggingFace