A 0.6B decision model on Qwen3-0.6B-Base from the DocsGPT team. Give it a state and typed questions (yes/no, a choice of up to 16 options, a 3- or 4-level score) and it returns calibrated probabilities in one pass, for RAG and agent checks.
An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.
Decides
choice, score, noul, classify, rank, route
choice, score, noul, classify, route
Architecture
arc-decide
kev
Fine-tuned from
qwen/qwen3-0.6b-base
qwen/qwen3.5-4b-base
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
83.8%
Calibration error
—
0.042
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between arc-decide and kev?
arc-decide is from Arc53 and kev from Jared Palmer. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only arc-decide answers rank. arc-decide is the smaller model, at 600M parameters to 4.0B. arc-decide is licensed mit; kev, apache-2.0.
Which is more accurate, arc-decide or kev?
Only kev publishes an accuracy figure (83.8% on transfer-v4 (locked, out of domain)); arc-decide does not, so there is no comparison to make without your own test.
Which is cheaper, arc-decide or kev?
arc-decide: Free (open weights). kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run arc-decide or kev locally?
Yes, both: systemone pull arc53/arc-decide and systemone pull jared-palmer/kev download the weights.
