Qwen3-VL-235B
Qwen3-VL-235B scores 41.2 out of 100 overall, which puts it in a tie for rank 19–29 of 36 models on the AI Vision Index. It is strongest at Not being fooled (65) and weakest at Counting (20). It beats the average of all 36 models in one of the six categories. It was tested on a smaller sample than most models, so its margin of error is wider and its single-test scores are rough.
Overall score41.295% interval 35.0–50.2
Rank19–29of 36 models (tied)
Cost per 1,000 answers$7.96
Seconds per answer1.8 s
Thinking effortdefault
Maker Alibaba
WeightsOpen weights
AccessAPI
Tested
Reading46
Counting20
Space, 3D and motion34
Spotting changes and errors42
Diagrams40
Not being fooled65
The bar is the score; the light band is the 95% interval. The overall score is the average of the six.
Reading
Reading a clock60
Reading a meter60
Eye chart20
Reading a label100
Reading a chart50
Test strips20
Adding up coins20
Traffic light from a car40
Counting
Counting objects20
Counting stacked goods40
Counting on a conveyor0
Space, 3D and motion
Which is nearer60
Which way it faces29
Same or mirror image0
Will it topple0
Match the render47
Which bay can I park in?78
Follow the hidden object25
Spotting changes and errors
Spot the change100
Shelf against plan40
Rendering glitch28
Check the invoice0
Diagrams
Follow the cable60
Follow the pipe40
Missing dimension20
Not being fooled
Absent objects100
Saying "I can't tell"100
Optical illusions40
Real or AI-made20
Scores are corrected for guessing: 0 is no better than a guess, 100 is always right. All models on every test
Neighbours on the leaderboard
- Qwen3.6-35B-A3B 43.0 Compare
- MiniMax M3 40.9 Compare
Badge for your site
HTML
<a href="https://aivisionindex.com/models/qwen3-vl-235b/"><img src="https://aivisionindex.com/badge/qwen3-vl-235b.svg" alt="Qwen3-VL-235B: ranked #19–29 of 36 on the AI Vision Index"></a>Markdown
[](https://aivisionindex.com/models/qwen3-vl-235b/)Results are CC BY 4.0, so you are free to reuse them if you credit the AI Vision Index. All results (JSON)