# Benjamin Babeshkin (SynACK): synack-decide

> A Gemma-4-26B-A4B decision model by Benjamin Babeshkin (SynACK): a JSON state and typed choice or yes/no questions go in, and one forward pass returns a probability for every option, with no generated text, over the /v1/systemone wire format.

- Page: https://systemonemodels.ai/benjamin-babeshkin/synack-decide
- API: https://api.systemonemodels.ai/v1/models/benjamin-babeshkin/synack-decide
- Download: `pip install systemonemodels && systemone pull benjamin-babeshkin/synack-decide`

## Facts

| | |
|---|---|
| Maker | Benjamin Babeshkin (SynACK) (https://systemonemodels.ai/benjamin-babeshkin) |
| Decides | choice, noul, classify, route |
| Architecture | synack-decide |
| Base model | google/gemma-4-26b-a4b-it |
| Parameters | 26B |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-10-04 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: SynACK private generalisation set (2,693 questions from 9 public datasets outside the Decision Index suite and the training data), the maker's run. Numbers are the publisher's own.

- Decision accuracy: 76.8%

- Median latency: 132 ms
- p95 latency: 360 ms

## Model card

<!-- generated by scripts/seed_catalog.py; edit content/models/catalog.yaml -->

# SynACK Decide 26B-A4B

A Gemma-4-26B-A4B decision model by Benjamin Babeshkin (SynACK): a JSON state and typed choice or yes/no questions go in, and one forward pass returns a probability for every option, with no generated text, over the /v1/systemone wire format.

About 4B parameters active per token; 51.6 GB in bf16, with GGUF (Q8_0, Q4_K_M) and 8-bit MLX builds from the maker. Up to 255 options; score was not trained. Calibrated in-distribution only and can be overconfident on unfamiliar compositions; mostly English. The card says it was built with Claude in Claude Code. Training data includes non-commercial sets (ANLI, Financial PhraseBank, RACE) and labels distilled from Kimi-K3; the maker says to review these before commercial use. The maker's own run of the third-party Decision Index 0.2.1 gives 59.5 (not verified by the board). SynACK is an independent project, not affiliated with Synack, Inc.

## What it decides

- **choice** — picks one option from a set
- **noul** — answers a yes/no question with one probability
- **classify** — assigns a category from a fixed taxonomy
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 26B |
| Base model | `google/gemma-4-26B-A4B-it` |
| Maker | Benjamin Babeshkin (SynACK) |
| Released | 2026-10-04 |
| License | apache-2.0 |
| Reported accuracy | 76.8% |
| Reported latency | 132 ms median / 360 ms p95 per Decision Index request, bf16, one RTX PRO 6000 |

## Get the weights

```bash
pip install systemonemodels
systemone pull benjamin-babeshkin/synack-decide
```

The files are served from the maker's Hugging Face repository, [`SkyPanther/synack-decide-26b-a4b`](https://huggingface.co/SkyPanther/synack-decide-26b-a4b), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/SkyPanther/synack-decide-26b-a4b)
- [GGUF builds](https://huggingface.co/SkyPanther/synack-decide-26b-a4b-GGUF)
- [Code](https://github.com/syn-ack-ai/synack-decide)
- [Write-up](https://syn-ack.ai/posts/teaching-a-small-model-to-decide)

---

*This page was opened by System One for Benjamin Babeshkin (SynACK), who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.ai/ · every System One model: https://systemonemodels.ai/system-one-models