Image-capable decision models. This board fills when an independent vision export is ingested. Text scores stay on Decision models. As of Oct 14, 2026, Decision models › Vision is uncrowned on isitsota (methodology v1.0).
| # | Model | State | Confidence |
|---|
Best page and recent changes
What can move this crown
- Decision Index Vision — primary, weight 1
Who is SOTA in Decision models › Vision?
As of Oct 14, 2026, Decision models › Vision is uncrowned on isitsota (methodology v1.0).
Since when is the Decision models › Vision crown current?
As of Oct 14, 2026, Decision models › Vision has an open crown.
What is a decision model?
A decision model takes state, as text or as images, plus a typed question. It returns a typed answer with probabilities rather than free text. Output types: noul (yes/no/unknown), choice, score, multi-label.
How is calibration ranked?
The calibration slice ranks the lowest ECE among models in the top quartile of accuracy, so a constant probability cannot take the slice. Brier breaks ECE ties.
Do vendor-reported decision numbers count?
Vendor-reported numbers are display-only at weight 0.