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.
StartLux's decision family in six sizes, 0.8B to a 35B-A3B mixture of experts. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server. Text, JSON or images, up to 256K tokens.
Decides
choice, score, noul, classify, rank, route
choice, score, noul
Architecture
arc-decide
startlux-decision
Fine-tuned from
qwen/qwen3-0.6b-base
—
License
mit
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
88.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
26 ms
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 startlux-decision?
arc-decide is from Arc53 and startlux-decision from StartLux. 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 4.7B. arc-decide is licensed mit; startlux-decision, cc-by-nc-4.0.
Which is more accurate, arc-decide or startlux-decision?
Only startlux-decision publishes an accuracy figure (88.3% on JevBench public set (231 items; 204 correct), maker's run); arc-decide does not, so there is no comparison to make without your own test.
Which is cheaper, arc-decide or startlux-decision?
arc-decide: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run arc-decide or startlux-decision locally?
Yes, both: systemone pull arc53/arc-decide and systemone pull startlux/startlux-decision download the weights.
—
Evaluation suite
—
JevBench public set (231 items; 204 correct), maker's run
