Arena benchmark
Vision
Published Vision results on the original Arena scale.
Updated Aug 7, 2026. Data as of 2026-08-07
Published models65
Categories11
Result typerating
Vision ranking
The table uses the source-provided overall rank and excludes review rows.
Top model distribution
Top published models on the same Arena scale.
What is the Vision Arena?
Registry-backed context for this evaluation surface.
Vision reports rating values and currently defines 11 evaluation categories.
Arena results are preference or task-outcome signals. They are not automatically equivalent to capability benchmark scores.
FAQ
Common questions about Vision.
Which model leads Vision?
Claude Fable 5 is currently ranked first on the published Arena scale.
What does Vision measure?
This Arena reports rating values across 11 configured evaluation categories.
Does this result affect the LLMBoard score?
No. Arena results remain a separate preference or task-outcome signal.
How many models are included?
65 canonical published model results are currently shown.