Claude Fable 5.1
Claude Fable 5.1 scores 69.6 out of 100 overall, which puts it in a tie for rank 6–9 of 36 models on the AI Vision Index. It is strongest at Diagrams (76) and weakest at Reading (63). It beats the average of all 36 models in all six categories.
Overall score69.695% interval 67.5–71.7
Rank6–9of 36 models (tied)
Cost per 1,000 answers$87.95
Seconds per answer5.5 s
Thinking effortdefault
Maker Anthropic
WeightsClosed weights
AccessAPI
Tested
Reading63
Counting63
Space, 3D and motion69
Spotting changes and errors75
Diagrams76
Not being fooled71
The bar is the score; the light band is the 95% interval. The overall score is the average of the six.
Reading
Reading a clock65
Reading a meter82
Eye chart25
Reading a label85
Reading a chart56
Test strips72
Adding up coins52
Traffic light from a car62
Counting
Counting objects42
Counting stacked goods60
Counting on a conveyor87
Space, 3D and motion
Which is nearer75
Which way it faces59
Same or mirror image40
Will it topple55
Match the render61
Which bay can I park in?100
Follow the hidden object92
Spotting changes and errors
Spot the change60
Shelf against plan90
Rendering glitch52
Check the invoice100
Diagrams
Follow the cable63
Follow the pipe75
Missing dimension90
Not being fooled
Absent objects94
Saying "I can't tell"99
Optical illusions44
Real or AI-made48
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
- Qwen3.8 Max 70.6 Compare
- Claude Haiku 5.5 63.5 Compare
Badge for your site
HTML
<a href="https://aivisionindex.com/models/claude-fable-5-1/"><img src="https://aivisionindex.com/badge/claude-fable-5-1.svg" alt="Claude Fable 5.1: ranked #6–9 of 36 on the AI Vision Index"></a>Markdown
[](https://aivisionindex.com/models/claude-fable-5-1/)Results are CC BY 4.0, so you are free to reuse them if you credit the AI Vision Index. All results (JSON)