# Standard Thinking: standard-one

> Standard Thinking's decision model. Ministral 3 8B with a merged LoRA, served through stock SGLang and an open jev-adapter that exposes /v1/systemone and scores the supplied options in one forward pass with per-type temperatures.

- Page: https://systemonemodels.tech/standard-thinking/standard-one
- API: https://api.systemonemodels.tech/v1/models/standard-thinking/standard-one
- Download: `pip install systemonemodels && systemone pull standard-thinking/standard-one`

## Facts

| | |
|---|---|
| Maker | Standard Thinking (https://systemonemodels.tech/standard-thinking) |
| Decides | choice, score, noul, classify, route |
| Architecture | standard-one |
| Base model | mistralai/ministral-3-8b-instruct-2512-bf16 |
| Parameters | 8.0B |
| Context | 8K tokens |
| Licence | apache-2.0 |
| Availability | Open weights + hosted API |
| Released | 2026-09-24 |
| Latest version | 2.0.0 |

## Hosted API

- Provider: Standard Thinking (https://standardthinking.ai)
- Docs: https://standardthinking.ai/docs/
- Input: — · Output: Free

## Reported evaluation

Suite: typed-decisions suite, 400 cases / 2,000 decisions (maker's served run, v2). Numbers are the publisher's own.

- Decision accuracy: 71.1%

- Median latency: 25.8 ms
- p95 latency: 41.9 ms

## Model card

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

# Standard One 8B

Standard Thinking's decision model. Ministral 3 8B with a merged LoRA, served through stock SGLang and an open jev-adapter that exposes /v1/systemone and scores the supplied options in one forward pass with per-type temperatures.

Version 2 (26 September) replaced the weights; v1 and v1.1 stay as tags. The maker reports 71.1% on a 400-case typed-decisions suite (2,000 decisions) and, on JevBench's public tiers, 100% easy, 93.1% standard and 55.0% hard (Jev 1.13 in its run: 72.1% on hard), with hard-tier ECE 0.184. At most 26 options per question; trained in nine languages; the Pixtral vision tower is kept but image decisions are not benchmarked. Training data is listed with its licences, several of them CC BY-SA. Siblings: Standard One 3B, LoRA repositories, FP8 and GGUF builds. Also served on the Standard API from $0.019 per million input tokens, output free. JevBench v1.4.2 ranked it 45th (76.6% public, 26.6% sealed).

## 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
- **classify** — assigns a category from a fixed taxonomy
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 8B |
| Base model | `mistralai/ministral-3-8b-instruct-2512-bf16` |
| Maker | Standard Thinking |
| Released | 2026-09-24 |
| License | apache-2.0 |
| Reported accuracy | 71.1% |
| Reported latency | 25.8 ms p50 / 41.9 ms p95 raw serial on one H200, SGLang 0.5.20, ~280 input tokens per decision |

## Hosted API

Served by **Standard Thinking** — $0/MTok output. [Get access](https://standardthinking.ai) · [API docs](https://standardthinking.ai/docs/).

## Get the weights

```bash
pip install systemonemodels
systemone pull standard-thinking/standard-one
```

The files are served from the maker's Hugging Face repository, [`StandardThinking/StandardOne-8B`](https://huggingface.co/StandardThinking/StandardOne-8B), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/StandardThinking/StandardOne-8B)
- [Benchmarks](https://huggingface.co/StandardThinking/StandardOne-8B/blob/main/docs/BENCHMARKS.md)
- [Standard One 3B](https://huggingface.co/StandardThinking/StandardOne-3B)
- [Standard API](https://standardthinking.ai)

---

*This page was opened by System One for Standard Thinking, 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