# 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/decision
Last updated: 2026-11-21
Methodology v1.0. Computed automatically.

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

## Decision models

https://isitsota.com/c/decision

### Primary benchmarks

- Decision Index Full: 60.3 (CI 59.8–60.8) on Nov 21, 2026 (#100 of 420).

On the category's weighted score it is 22.0 points behind #1 karpo-decision-31B and 0.3 behind the next model up, Qwen Decision 27B noncausal LoRA.

### Nearby on the board

| # | Model | Category score |
| ---: | --- | ---: |
| 94 | [OneJev1.6-27B](https://isitsota.com/m/onejev1-6-27b.md) | 78.6 |
| 95 | [decider chat on Gemma-4-31B-it (Mapika, frozen base, inference technique)](https://isitsota.com/m/decider-chat-gemma4-31b.md) | 78.3 |
| 96 | [Qwen Decision 27B noncausal LoRA](https://isitsota.com/m/qwen-decision-27b-noncausal.md) | 78.3 |
| 97 | **garum (Gemma 4 31B)** | 78.0 |
| 98 | [baselabs elephant-1 (9B)](https://isitsota.com/m/elephant-1-baselabs.md) | 77.7 |
| 99 | [Standard One 35B SH (v1)](https://isitsota.com/m/standard-one-35b-sh-v1.md) | 77.1 |
| 100 | [NTele-Hybrid-27B-v1](https://isitsota.com/m/ntele-hybrid-27b-v1.md) | 76.8 |

## Related

- Model page: https://isitsota.com/m/garum.md
- 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
