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.
Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens.
Decides
choice, score, noul, classify, rank, route
choice, noul, score
Architecture
arc-decide
canopy-jev
Fine-tuned from
qwen/qwen3-0.6b-base
qwen/qwen3.8-27b
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
87.4%
Calibration error
—
—
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 canopy-jev?
arc-decide is from Arc53 and canopy-jev from Ruoxi Qiu. Both have open weights you can download and run. Both answer choice, score and noul questions. Only arc-decide answers classify, rank and route. arc-decide is the smaller model, at 600M parameters to 27B. arc-decide is licensed mit; canopy-jev, apache-2.0.
Which is more accurate, arc-decide or canopy-jev?
Only canopy-jev publishes an accuracy figure (87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer); arc-decide does not, so there is no comparison to make without your own test.
Which is cheaper, arc-decide or canopy-jev?
arc-decide: Free (open weights). canopy-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run arc-decide or canopy-jev locally?
Yes, both: systemone pull arc53/arc-decide and systemone pull camellia86/canopy-jev download the weights.
—
Evaluation suite
—
JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer
