As of Oct 15, 2026, Hopper 12B trained (gemma-4-12B-it frozen + LoRA r32 unmerged, one forward pass, self-hosted) is ranked #91 in Decision models (since Oct 15, 2026; sources Decision Index Full; methodology v1.0). Ranked #91 in Decision models.
The ruling, in plain English
Ranked #91 in Decision models.
Reliability
Index bins for Hopper 12B trained (gemma-4-12B-it frozen + LoRA r32 unmerged, one forward pass, self-hosted). Confidence on the horizontal axis, accuracy on the vertical axis.
Median 289.7 ms, same GPU.
$0.0289 per 1,000 decisions.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full Hopper 12B (trained) | 47.27 46.8–47.8 | 2026-10-14 | INDEP. | snap_decision-index_2026-10-14_release-v3|decision-index-0.3.2 |
Where it sits in the succession
Crown intervals for this model are still empty.
Where it is not the crown
| Category | This model | Why |
|---|---|---|
| Decision models | #91 in this category | Ranked #91 in Decision models. |
Related pages
Is Hopper 12B trained (gemma-4-12B-it frozen + LoRA r32 unmerged, one forward pass, self-hosted) SOTA?
Best current rank: #91 in Decision models, as of Oct 15, 2026.
What is Hopper 12B trained (gemma-4-12B-it frozen + LoRA r32 unmerged, one forward pass, self-hosted) best at?
As of Oct 15, 2026, Hopper 12B trained (gemma-4-12B-it frozen + LoRA r32 unmerged, one forward pass, self-hosted) is ranked #91 in Decision models (since Oct 15, 2026; sources Decision Index Full).
How does Hopper 12B trained (gemma-4-12B-it frozen + LoRA r32 unmerged, one forward pass, self-hosted) rank in Decision models?
Best current rank: #91 in Decision models, as of Oct 15, 2026.