Claude Opus 5.5
Claude Opus 5.5 scores 76.5 out of 100 overall, which puts it in a tie for rank 4–5 of 36 models on the AI Vision Index. It is strongest at Diagrams (90) and weakest at Counting (63). It beats the average of all 36 models in all six categories.
Overall score76.595% interval 74.8–78.3
Rank4–5of 36 models (tied)
Cost per 1,000 answers$26.16
Seconds per answer3.9 s
Thinking effortdefault
Maker Anthropic
WeightsClosed weights
AccessAPI
Tested
Reading75
Counting63
Space, 3D and motion71
Spotting changes and errors84
Diagrams90
Not being fooled76
The bar is the score; the light band is the 95% interval. The overall score is the average of the six.
Reading
Reading a clock91
Reading a meter85
Eye chart44
Reading a label88
Reading a chart76
Test strips70
Adding up coins67
Traffic light from a car78
Counting
Counting objects43
Counting stacked goods52
Counting on a conveyor92
Space, 3D and motion
Which is nearer70
Which way it faces79
Same or mirror image20
Will it topple59
Match the render82
Which bay can I park in?100
Follow the hidden object88
Spotting changes and errors
Spot the change74
Shelf against plan95
Rendering glitch67
Check the invoice100
Diagrams
Follow the cable81
Follow the pipe98
Missing dimension92
Not being fooled
Absent objects93
Saying "I can't tell"97
Optical illusions70
Real or AI-made44
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
- Gemini 4 Argon 77.2 Compare
- Claude Sonnet 5.5 71.0 Compare
Badge for your site
HTML
<a href="https://aivisionindex.com/models/claude-opus-5-5/"><img src="https://aivisionindex.com/badge/claude-opus-5-5.svg" alt="Claude Opus 5.5: ranked #4–5 of 36 on the AI Vision Index"></a>Markdown
[](https://aivisionindex.com/models/claude-opus-5-5/)Results are CC BY 4.0, so you are free to reuse them if you credit the AI Vision Index. All results (JSON)