MiMo v2.6 Pro
MiMo v2.6 Pro 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 Spotting changes and errors (58) and weakest at Counting (19). It beats the average of all 36 models in one of the six categories.
Overall score40.395% interval 38.6–42.6
Rank19–29of 36 models (tied)
Cost per 1,000 answers$4.60
Seconds per answer54.7 s
Thinking effortdefault
Maker Xiaomi
WeightsOpen weights
AccessAPI
Tested
Reading36
Counting19
Space, 3D and motion37
Spotting changes and errors58
Diagrams46
Not being fooled46
The bar is the score; the light band is the 95% interval. The overall score is the average of the six.
Reading
Reading a clock9
Reading a meter32
Eye chart8
Reading a label69
Reading a chart37
Test strips49
Adding up coins32
Traffic light from a car52
Counting
Counting objects18
Counting stacked goods23
Counting on a conveyor17
Space, 3D and motion
Which is nearer66
Which way it faces29
Same or mirror image0
Will it topple12
Match the render32
Which bay can I park in?88
Follow the hidden object28
Spotting changes and errors
Spot the change55
Shelf against plan71
Rendering glitch19
Check the invoice87
Diagrams
Follow the cable51
Follow the pipe32
Missing dimension54
Not being fooled
Absent objects92
Saying "I can't tell"79
Optical illusions8
Real or AI-made5
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
Badge for your site
HTML
<a href="https://aivisionindex.com/models/mimo-v2-6-pro/"><img src="https://aivisionindex.com/badge/mimo-v2-6-pro.svg" alt="MiMo v2.6 Pro: ranked #19–29 of 36 on the AI Vision Index"></a>Markdown
[](https://aivisionindex.com/models/mimo-v2-6-pro/)Results are CC BY 4.0, so you are free to reuse them if you credit the AI Vision Index. All results (JSON)