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
Qwen3-235B-A22B-Instruct-2507
Open
Share
Add to comparison
Tool use
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#79
68.9 points · 180 models
Open-weight rank
#25
76.8 points · 109 models
Data coverage
28 items
2 sources · updated through 2026-07-16
Domain performance
Coding
#86 / 160
68.3
Research
#79 / 174
79
Agents
#73 / 125
65.2
Evaluation highlights
All evaluations
ZebraLogic
Reasoning · Qwen3 2507 Hugging Face Model Card
95%
1
/ 39
MultiPL-E
Coding · Qwen3 2507 Hugging Face Model Card
87.9%
1
/ 31
TAU1-Retail
Agents · Qwen3 2507 Hugging Face Model Card
71.3%
1
/ 9
IFEval
Instruction following · Qwen3 2507 Hugging Face Model Card
88.7%
14
/ 30
Creative Writing v3
Writing · Qwen3 2507 Hugging Face Model Card
87.5%
1
/ 42
SimpleQA
Knowledge · Qwen3 2507 Hugging Face Model Card
54.3%
1
/ 13
Basic information
Context (input / output)
1M / 33K
Parameters
235B / 22B active
Release date
2025-07
License
Apache 2.0
Input modalities
Text
Output modalities
Text
Modes
Instruct / non-thinking only
Version
2507
Active parameters
22B
Availability
vLLM · BF16
Deployment options
BF16 · 8 × 141 GB VRAM
Related links
Official site
HuggingFace
Version relationships
Qwen3-235B-A22B family
Qwen3-235B-A22B
2025-04 · Same series
Qwen3-235B-A22B-Base
2025-04 · Same series
Qwen3-235B-A22B-Instruct-2507
Current
2025-07 · Current model
Qwen3-235B-A22B-Thinking-2507
2025-07 · Same series