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.
Laya fine-tune that scans untrusted text (extracted files, knowledge-base documents, agent skills, tool descriptions) for prompt injection and data exfiltration in English and German, as a noul question answered in one forward pass. 322M parameters, PyTorch and ONNX.
Decides
choice, score, noul, classify, rank, route
noul, classify
Architecture
arc-decide
laya
Fine-tuned from
qwen/qwen3-0.6b-base
convaiinnovations/laya-multilingual
License
mit
Unspecified; training data includes CC BY-NC-SA 4.0 material (non-commercial), not relicensed
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
95.4 ms
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 laya-cybersec?
arc-decide is from Arc53 and laya-cybersec from TextCortex. Both have open weights you can download and run. Both answer noul and classify questions. Only arc-decide answers choice, score, rank and route. laya-cybersec is the smaller model, at 322M parameters to 600M. arc-decide is licensed mit; laya-cybersec, other.
Which is more accurate, arc-decide or laya-cybersec?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, arc-decide or laya-cybersec?
arc-decide: Free (open weights). laya-cybersec: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run arc-decide or laya-cybersec locally?
Yes, both: systemone pull arc53/arc-decide and systemone pull textcortex/laya-cybersec download the weights.
p95 latency
—
149 ms
Evaluation suite
—
TextCortex saved run: 279 single-window inputs, PyTorch batch one
