Claude Fable 5.2
Claude Fable 5.2 scores 80.7 out of 100 overall, which puts it in a tie for rank 2–3 of 36 models on the AI Vision Index. It is strongest at Diagrams (95) and weakest at Counting (64). It beats the average of all 36 models in all six categories.
Overall score80.795% interval 78.6–82.8
Rank2–3of 36 models (tied)
Cost per 1,000 answers$53.10
Seconds per answer– (no comparable timing yet)
Thinking effortdefault
Maker Anthropic
WeightsNot checked yet
AccessAPI
Tested
Reading81
Counting64
Space, 3D and motion86
Spotting changes and errors86
Diagrams95
Not being fooled72
The bar is the score; the light band is the 95% interval. The overall score is the average of the six.
Reading
Reading a clock95
Reading a meter95
Eye chart52
Reading a label90
Reading a chart75
Test strips78
Adding up coins70
Traffic light from a car96
Counting
Counting objects52
Counting stacked goods42
Counting on a conveyor98
Space, 3D and motion
Which is nearer80
Which way it faces82
Same or mirror image75
Will it topple70
Match the render93
Which bay can I park in?100
Follow the hidden object100
Spotting changes and errors
Spot the change82
Shelf against plan100
Rendering glitch64
Check the invoice97
Diagrams
Follow the cable90
Follow the pipe100
Missing dimension95
Not being fooled
Absent objects94
Saying "I can't tell"96
Optical illusions59
Real or AI-made40
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
- GPT-6.1 Sol 81.3 Compare
- Gemini 4 Argon 77.2 Compare
Badge for your site
HTML
<a href="https://aivisionindex.com/models/claude-fable-5-2/"><img src="https://aivisionindex.com/badge/claude-fable-5-2.svg" alt="Claude Fable 5.2: ranked #2–3 of 36 on the AI Vision Index"></a>Markdown
[](https://aivisionindex.com/models/claude-fable-5-2/)Results are CC BY 4.0, so you are free to reuse them if you credit the AI Vision Index. All results (JSON)