Decision-1.0-Nox-4B

Nox, Latin for night.

Give Nox a state, questions and possible answers. It returns typed decisions and probabilities, with labels defined at runtime.

Decision family

Type	Use it for	Output
Choice	Route a request or choose among 2–255 actions.	Selected ID + distribution
Noul	Check a condition against supplied evidence.	P(true)
Score	Apply 2–10 ordered rubric descriptions.	Expected index + distribution

Measured capability

73.09% weighted accuracy across 3,766 decisions and 54 tasks: +2.99 points over Kev-4B on the same benchmark.

Model	Size	Decisions	Composition	Reading	Inference	Transfer	Overall
Nox-4B	4B	83.00	51.79	79.06	86.25	69.60	73.09
Lux-9B	9B	84.10	51.75	89.69	91.46	77.34	76.94
Kev-9B	9B	76.75	45.75	86.72	83.54	79.25	71.89
Kev-4B	4B	71.90	48.54	81.88	84.58	76.10	70.09
Qwen3.5-9B	9B	73.91	44.62	89.84	79.58	73.23	69.73
Decider	2B	64.01	46.58	92.03	84.38	69.31	67.71
Qwen3.5-4B	4B	69.89	43.33	87.97	79.79	68.83	67.29
Sol-2B	2B	73.75	46.08	76.56	84.17	57.07	66.32
Eos-0.8B	0.8B	65.94	46.04	70.31	81.67	52.01	61.89
Kev-0.8B	0.8B	60.14	42.29	67.81	68.75	61.19	58.28
Qwen3.5-2B	2B	57.12	39.00	73.75	72.29	56.31	57.24
Kai-0.6B	0.6B	57.96	40.83	54.69	69.79	48.37	53.52
Laya · English	0.421B	56.54	35.33	51.41	63.75	53.06	51.03
Laya · Multilingual	0.322B	47.25	38.92	50.78	57.29	47.13	47.19
Jev	—	79.10	66.38	94.53	89.79	87.19	81.05

Accuracy (%). Overall weights: Decisions 30%, Composition 25%, Reading 15%, Inference 15%, Transfer 15%. These outcome-informed product-priority weights were chosen after observing results; reweighting is not a training improvement. Bold marks Decision-family cells above every external open or untuned reference for that metric, excluding Jev and the other Decision models.

All 54 tasks · Order, missing-evidence and calibration diagnostics · Methods and uncertainty

More questions, one request

Distinct Choice questions at a fixed 499 input tokens per question. Thirty measurements per point across six independently loaded processes on an otherwise idle AMD gfx942 GPU. Python latency includes tokenization and inference; loading and network are excluded. p50, p95 and memory.

Use Nox-4B

Use the official TypeSafe Python SDK with your SystemOne-compatible endpoint, configured to serve Decision-1.0-Nox-4B. Replace the example URL and API key with your own.

pip install typesafe-sdk

from typesafe_sdk import Choice, Noul, TypeSafeClient

with TypeSafeClient(
    api_key="YOUR_ENDPOINT_API_KEY",
    base_url="https://your-decision-endpoint.example",
    model="Decision-1.0-Nox-4B",
) as client:
    result = client.system_one(
        state="Customer reports a duplicate charge and asks for a refund.",
        questions={
            "route": Choice(
                instructions="Which team should handle this request?",
                criteria={"billing": "Payments and refunds", "technical": "Product faults"},
            ),
            "refund_requested": Noul(instructions="Did the customer request a refund?"),
        },
    )
    print(result.choices["route"].choice)
    print(result.nouls["refund_requested"].noul)

The same request with curl:

curl -X POST 'https://your-decision-endpoint.example/v1/systemone' \
  -H 'Authorization: Bearer YOUR_ENDPOINT_API_KEY' \
  -H 'Content-Type: application/json' \
  --data-raw '{
  "model": "Decision-1.0-Nox-4B",
  "state": "Customer reports a duplicate charge and asks for a refund.",
  "questions": {
    "route": {
      "type": "choice",
      "instructions": "Which team should handle this request?",
      "criteria": {
        "billing": "Payments and refunds",
        "technical": "Product faults"
      }
    },
    "refund_requested": {
      "type": "noul",
      "instructions": "Did the customer request a refund?"
    }
  }
}'

Typed request and response guide · Model runtime requirements

Choice candidates with a null description use their ID text, which may increase input tokens.

The complete state, question and candidates must fit 16,384 tokens; overflow is rejected. The bundled normalization profile loads automatically. AMD gfx942 is validated; CPU/MPS are unsupported and NVIDIA is unqualified. Use a fresh Python process when switching profiles.

Architecture

A causal Qwen3.5 text backbone combines gated linear and full attention. A shared candidate head reads candidate endpoints and the final query vector. Each question uses one forward pass; questions run independently in batches of eight.

Candidate head · Vector architecture · Inference code

Adapted from Qwen3.5-4B. It evaluates supplied evidence without live retrieval; confidence does not guarantee correctness. License · Attributions.