Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite scores 40.3 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 (53) and weakest at Counting (22). It beats the average of all 36 models in none of the six categories.
Overall score40.395% interval 38.7–41.8
Rank19–29of 36 models (tied)
Cost per 1,000 answers$0.34
Seconds per answer2.6 s
Thinking effortdefault
Maker Google
WeightsClosed weights
AccessAPI
Tested
Reading40
Counting22
Space, 3D and motion39
Spotting changes and errors44
Diagrams44
Not being fooled53
The bar is the score; the light band is the 95% interval. The overall score is the average of the six.
Reading
Reading a clock23
Reading a meter38
Eye chart4
Reading a label80
Reading a chart53
Test strips49
Adding up coins20
Traffic light from a car51
Counting
Counting objects16
Counting stacked goods30
Counting on a conveyor18
Space, 3D and motion
Which is nearer47
Which way it faces42
Same or mirror image0
Will it topple32
Match the render54
Which bay can I park in?76
Follow the hidden object24
Spotting changes and errors
Spot the change32
Shelf against plan50
Rendering glitch39
Check the invoice55
Diagrams
Follow the cable50
Follow the pipe19
Missing dimension62
Not being fooled
Absent objects86
Saying "I can't tell"89
Optical illusions0
Real or AI-made37
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
- MiMo v2.6 Pro 40.3 Compare
- Gemma 4 31B 38.8 Compare
Badge for your site
HTML
<a href="https://aivisionindex.com/models/gemini-3-5-flash-lite/"><img src="https://aivisionindex.com/badge/gemini-3-5-flash-lite.svg" alt="Gemini 3.5 Flash-Lite: ranked #19–29 of 36 on the AI Vision Index"></a>Markdown
[](https://aivisionindex.com/models/gemini-3-5-flash-lite/)Results are CC BY 4.0, so you are free to reuse them if you credit the AI Vision Index. All results (JSON)