# FLock.io: this-that-model

> FLock.io's typed-decision model, fine-tuned from Mapika's decider-2b. Reads one hidden state per question and scores the declared options, so an answer outside the list cannot occur; several questions about one state share a forward pass.

- Page: https://systemonemodels.tech/flock-io/this-that-model
- API: https://api.systemonemodels.tech/v1/models/flock-io/this-that-model
- Download: `pip install systemonemodels && systemone pull flock-io/this-that-model`

## Facts

| | |
|---|---|
| Maker | FLock.io (https://systemonemodels.tech/flock-io) |
| Decides | choice, score, noul |
| Architecture | this-that |
| Base model | mapika/decider |
| Parameters | 1.9B |
| Licence | mit |
| Availability | Open weights |
| Released | 2026-09-20 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: limberc/this-that-complex-decisions (1,710 questions, FLock's benchmark). Numbers are the publisher's own.

- Decision accuracy: 87.8%

- Median latency: 31.4 ms

## Model card

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

# this-that-model-1.2

FLock.io's typed-decision model, fine-tuned from Mapika's decider-2b. Reads one hidden state per question and scores the declared options, so an answer outside the list cannot occur; several questions about one state share a forward pass.

Version 1.2 (23 September) targets policy rules however they are phrased, including rules written in the negative, and rules that compose. On FLock's public 1,710-question complex-decision benchmark it scores 0.878 (1.1: 0.775, 1.0: 0.406) and 0.909 on a held-out composed-rule ladder. Up to 255 options. Released under MIT, adapted from the Apache-2.0 decider-2b, which this registry already lists; the pip package is thisthat. The third-party Decision Index 0.2.1 scores 1.2 at 28.14.

## What it decides

- **choice** — picks one option from a set
- **score** — places the input on an ordered scale
- **noul** — answers a yes/no question with one calibrated probability

## At a glance

| | |
|---|---|
| Parameters | 1.88B |
| Base model | `mapika/decider-2b` |
| Maker | FLock.io |
| Released | 2026-09-20 |
| License | mit |
| Reported accuracy | 87.8% |
| Reported latency | 31.4 ms per question on an RTX 5080 Laptop GPU |

## Get the weights

```bash
pip install systemonemodels
systemone pull flock-io/this-that-model
```

The files are served from the maker's Hugging Face repository, [`flock-io/this-that-model-1.2`](https://huggingface.co/flock-io/this-that-model-1.2), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/flock-io/this-that-model-1.2)
- [Inference code](https://github.com/FLock-io/this-that-model)
- [Benchmark](https://huggingface.co/datasets/limberc/this-that-complex-decisions)
- [this-that-model-1.0](https://huggingface.co/flock-io/this-that-model-1.0)

---

*This page was opened by System One for FLock.io, who can claim the organisation and take it over at any time.*

---

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