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.
A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
Decides
choice, score, noul, classify, rank, route
choice, score, noul, classify, route
Architecture
arc-decide
julia
Fine-tuned from
qwen/qwen3-0.6b-base
jhu-clsp/mmbert-small
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
73.2%
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 julia-1?
arc-decide is from Arc53 and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only arc-decide answers rank. julia-1 is the smaller model, at 144M parameters to 600M. arc-decide is licensed mit; julia-1, apache-2.0.
Which is more accurate, arc-decide or julia-1?
Only julia-1 publishes an accuracy figure (73.2% on typed-decisions test set (400 cases, 2,000 questions)); arc-decide does not, so there is no comparison to make without your own test.
Which is cheaper, arc-decide or julia-1?
arc-decide: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run arc-decide or julia-1 locally?
Yes, both: systemone pull arc53/arc-decide and systemone pull supersonic-labs/julia-1 download the weights.
—
Evaluation suite
—
typed-decisions test set (400 cases, 2,000 questions)
