VERIFIEDOct 142026
Is Winnow-12B state of the art?
#57Best current rank: #57 in Decision models, as of Oct 14, 2026.
As of Oct 14, 2026, Winnow-12B is ranked #57 in Decision models (since Oct 14, 2026; sources Decision Index Full and JevBench; methodology v1.0). Ranked #57 in Decision models.
Why
The ruling, in plain English
Ranked #57 in Decision models.
Calibration
Reliability
Index bins for Winnow-12B. Confidence on the horizontal axis, accuracy on the vertical axis.
Median 72.5 ms, same GPU.
$0.0281 per 1,000 decisions.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full Winnow-12B · q8 | 49.27 48.8–49.8 | 2026-10-14 | INDEP. | snap_decision-index_2026-10-14_release-v3|decision-index-0.3.2 |
| JevBench Winnow-12B Q8 · q8 | 71.24586176250037 70.7–71.7 | 2026-10-08 | INDEP. | snap_jevbench_2026-10-08_v1.6.1|jevbench-v1.6.1 |
Reign history
Where it sits in the succession
Crown intervals for this model are still empty.
Honest about the gaps
Where it is not the crown
| Category | This model | Why |
|---|---|---|
| Decision models | #57 in this category | Ranked #57 in Decision models. |
Links
Related pages
Is Winnow-12B SOTA?
Best current rank: #57 in Decision models, as of Oct 14, 2026.
What is Winnow-12B best at?
As of Oct 14, 2026, Winnow-12B is ranked #57 in Decision models (since Oct 14, 2026; sources Decision Index Full and JevBench).
How does Winnow-12B rank in Decision models?
Best current rank: #57 in Decision models, as of Oct 14, 2026.