# Is garum (Gemma 4 31B) SOTA?

Best current rank: #97 in Decision models, as of Nov 22, 2026.

As of Nov 22, 2026, garum (Gemma 4 31B) is ranked #97 in Decision models (since Nov 22, 2026; sources Decision Index Full; methodology v1.0). Ranked #97 in Decision models.

Canonical: https://isitsota.com/m/garum
Last updated: 2026-11-21
Methodology v1.0. Computed automatically.

- Decision models: #97 in Decision models — Ranked #97 in Decision models.

## At a glance

garum (Gemma 4 31B) is an open-weights text model from Unknown; 31B parameters and no public price.

### How it scores

- On Decision Index Full it scores 60.3 (CI 59.8–60.8), #100 of 420 (top 24%); 13.6 behind karpo-decision-31B; Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits) is 0.5 above and level with baselabs elephant-1 (9B) below.
- On Decision Index ECE it scores 5.1%, #155 of 420 (top 37%); 4.0 pts behind KnowLine 9B Gen2; level with KnowLine 4B Gen5 above and level with WeMM-JEV-27B below.
- On Decision Index Brier it scores 36.7%, #187 of 419 (top 45%); 16.3 pts behind lg-decision-4B; level with Cerno 4B v1.1 above and Xor 26B-A4B v1.1 is 0.1 pts below.

### History

First result on isitsota: Nov 21, 2026. Best overall rank so far: #97 in Decision models, first held Nov 22, 2026.


## Related

- Lab: [Unknown](https://isitsota.com/labs/unknown.md)
- Category: [Decision models](https://isitsota.com/c/decision.md)
- JSON: https://api.isitsota.com/v1/models/garum
