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.
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
noul, classify
choice, score, noul
Architecture
laya
startlux-decision
Fine-tuned from
convaiinnovations/laya-multilingual
—
License
Unspecified; training data includes CC BY-NC-SA 4.0 material (non-commercial), not relicensed
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
95.4 ms
26 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 laya-cybersec and startlux-decision?
laya-cybersec is from TextCortex and startlux-decision from StartLux. Both have open weights you can download and run. Both answer noul questions. Only laya-cybersec answers classify. Only startlux-decision answers choice and score. startlux-decision reads up to 256K tokens of state, against 1K tokens for laya-cybersec. laya-cybersec is the smaller model, at 322M parameters to 4.7B. laya-cybersec is licensed other; startlux-decision, cc-by-nc-4.0.
Which is more accurate, laya-cybersec or startlux-decision?
Only startlux-decision publishes an accuracy figure (88.3% on JevBench public set (231 items; 204 correct), maker's run); laya-cybersec does not, so there is no comparison to make without your own test.
Which is cheaper, laya-cybersec or startlux-decision?
laya-cybersec: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, laya-cybersec or startlux-decision?
By their publishers’ figures, startlux-decision answers in about 26 ms at the median and laya-cybersec in about 95.4 ms — measured on different hardware, so treat it as a rough guide.
Can I run laya-cybersec or startlux-decision locally?
Yes, both: systemone pull textcortex/laya-cybersec and systemone pull startlux/startlux-decision download the weights.
p95 latency
149 ms
—
Evaluation suite
TextCortex saved run: 279 single-window inputs, PyTorch batch one
JevBench public set (231 items; 204 correct), maker's run
