Hunyuan HY4
Hunyuan HY4 scores 37.9 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 (64) and weakest at Counting (7). 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 score37.995% interval 31.2–46.5
Rank19–29of 36 models (tied)
Cost per 1,000 answers$5.71
Seconds per answer170.6 s
Thinking effortdefault
Maker Tencent
WeightsClosed weights
AccessAPI
Tested
Reading33
Counting7
Space, 3D and motion24
Spotting changes and errors53
Diagrams47
Not being fooled64
The bar is the score; the light band is the 95% interval. The overall score is the average of the six.
Reading
Reading a clock40
Reading a meter40
Eye chart40
Reading a label60
Reading a chart25
Test strips0
Adding up coins20
Traffic light from a car40
Counting
Counting objects0
Counting stacked goods0
Counting on a conveyor20
Space, 3D and motion
Which is nearer20
Which way it faces29
Same or mirror image0
Will it topple0
Match the render20
Which bay can I park in?55
Follow the hidden object45
Spotting changes and errors
Spot the change20
Shelf against plan60
Rendering glitch52
Check the invoice79
Diagrams
Follow the cable40
Follow the pipe20
Missing dimension80
Not being fooled
Absent objects100
Saying "I can't tell"67
Optical illusions70
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
- Seed 2.1 Turbo 38.3 Compare
- Qwen3.5-9B 29.5 Compare
Badge for your site
HTML
<a href="https://aivisionindex.com/models/hunyuan-hy4/"><img src="https://aivisionindex.com/badge/hunyuan-hy4.svg" alt="Hunyuan HY4: ranked #19–29 of 36 on the AI Vision Index"></a>Markdown
[](https://aivisionindex.com/models/hunyuan-hy4/)Results are CC BY 4.0, so you are free to reuse them if you credit the AI Vision Index. All results (JSON)