Perceptron Mk1.5
Perceptron Mk1.5 scores 28.8 out of 100 overall, which puts it in a tie for rank 30–31 of 36 models on the AI Vision Index. It is strongest at Not being fooled (47) and weakest at Counting (11). It beats the average of all 36 models in none of the six categories. It cannot take the two video tests, so its score covers the other tests.
Overall score28.895% interval 27.4–30.4
Rank30–31of 36 models (tied)
Cost per 1,000 answers$0.20
Seconds per answer7.5 s
Thinking effortdefault
Maker Perceptron
WeightsClosed weights
AccessAPI
Tested
Reading39
Counting11
Space, 3D and motion36
Spotting changes and errors16
Diagrams24
Not being fooled47
The bar is the score; the light band is the 95% interval. The overall score is the average of the six.
Reading
Reading a clock51
Reading a meter45
Eye chart1
Reading a label69
Reading a chart51
Test strips41
Adding up coins4
Traffic light from a car54
Counting
Counting objects14
Counting stacked goods8
Counting on a conveyorNot supported—
Space, 3D and motion
Which is nearer62
Which way it faces27
Same or mirror image0
Will it topple23
Match the render56
Which bay can I park in?47
Follow the hidden objectNot supported—
Spotting changes and errors
Spot the change32
Shelf against plan18
Rendering glitch7
Check the invoice6
Diagrams
Follow the cable34
Follow the pipe14
Missing dimension23
Not being fooled
Absent objects91
Saying "I can't tell"76
Optical illusions0
Real or AI-made21
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
- Qwen3.5-9B 29.5 Compare
- Qwen3-VL-8B 26.0 Compare
Badge for your site
HTML
<a href="https://aivisionindex.com/models/perceptron-mk1-5/"><img src="https://aivisionindex.com/badge/perceptron-mk1-5.svg" alt="Perceptron Mk1.5: ranked #30–31 of 36 on the AI Vision Index"></a>Markdown
[](https://aivisionindex.com/models/perceptron-mk1-5/)Results are CC BY 4.0, so you are free to reuse them if you credit the AI Vision Index. All results (JSON)