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
Qwen3.6-35B-A3B
Open
Share
Add to comparison
Tool use · Reasoning
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#63
71.4 points · 180 models
Open-weight rank
#22
77.9 points · 109 models
Data coverage
52 items
2 sources · updated through 2026-04-22
Domain performance
Coding
#71 / 160
70.9
Research
#68 / 174
80.8
Agents
#62 / 125
68
Vision
#26 / 65
82.4
Evaluation highlights
All evaluations
MMLU-Redux
Reasoning · Qwen3.6-27B Technical Report
93.3%
19
/ 102
RealWorldQA
Multimodal · Qwen3.6-27B Technical Report
85.3%
2
/ 10
QwenWebBench
Coding · Qwen3.6-27B Technical Report
1,397pts
4
/ 8
TAU3-Bench
Agents · Qwen3.6-35B-A3B Technical Report
67.2%
5
/ 7
C-Eval
Chinese · Qwen3.6-27B Technical Report
90%
18
/ 64
OmniDocBench 1.5
Multimodal · Qwen3.6-35B-A3B Technical Report
89.9%
7
/ 28
Basic information
Context (input / output)
262K / 33K
Parameters
35B / 3B active
Release date
2026-04
License
Apache 2.0
Input modalities
Text · Image
Output modalities
Text
Active parameters
3B
Availability
vLLM · FP8
Deployment options
FP8 · 42 GB VRAM
Related links
Official site
HuggingFace