Qwen3.8 Flash
Qwen3.8 Flash scores 56.4 out of 100 overall, which puts it in a tie for rank 10–18 of 36 models on the AI Vision Index. It is strongest at Diagrams (66) and weakest at Counting (41). It beats the average of all 36 models in five of the six categories.
Overall score56.495% interval 55.0–57.8
Rank10–18of 36 models (tied)
Cost per 1,000 answers$3.04
Seconds per answer48.0 s
Thinking effortdefault
Maker Alibaba
WeightsClosed weights
AccessAPI
Tested
Reading58
Counting41
Space, 3D and motion55
Spotting changes and errors64
Diagrams66
Not being fooled55
The bar is the score; the light band is the 95% interval. The overall score is the average of the six.
Reading
Reading a clock65
Reading a meter55
Eye chart38
Reading a label77
Reading a chart46
Test strips66
Adding up coins49
Traffic light from a car68
Counting
Counting objects34
Counting stacked goods27
Counting on a conveyor61
Space, 3D and motion
Which is nearer73
Which way it faces59
Same or mirror image0
Will it topple51
Match the render55
Which bay can I park in?96
Follow the hidden object53
Spotting changes and errors
Spot the change74
Shelf against plan68
Rendering glitch25
Check the invoice89
Diagrams
Follow the cable57
Follow the pipe54
Missing dimension87
Not being fooled
Absent objects92
Saying "I can't tell"92
Optical illusions2
Real or AI-made35
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
- Qwen3.8-27B 59.0 Compare
- Grok 4.7 54.9 Compare
Badge for your site
HTML
<a href="https://aivisionindex.com/models/qwen3-8-flash/"><img src="https://aivisionindex.com/badge/qwen3-8-flash.svg" alt="Qwen3.8 Flash: ranked #10–18 of 36 on the AI Vision Index"></a>Markdown
[](https://aivisionindex.com/models/qwen3-8-flash/)Results are CC BY 4.0, so you are free to reuse them if you credit the AI Vision Index. All results (JSON)