Ultra-small English encoders (17M, 68M and 395M) fine-tuned from Ettin rerankers. Each answers choice, noul and score questions with a probability per candidate and no generated text. Experimental v0 by one developer; the weights have no licence assigned yet.
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, noul, score
noul, classify
Architecture
bekko
laya
Fine-tuned from
cross-encoder/ettin-reranker-400m-v1
convaiinnovations/laya-multilingual
License
Unassigned: the weights licence is not finalised (treated as non-commercial); training code 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
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 bekko-system-one and laya-cybersec?
bekko-system-one is from Yuichi Tateno (hotchpotch) and laya-cybersec from TextCortex. Both have open weights you can download and run. Both answer noul questions. Only bekko-system-one answers choice and score. Only laya-cybersec answers classify. laya-cybersec is the smaller model, at 322M parameters to 395M.
Which is more accurate, bekko-system-one or laya-cybersec?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, bekko-system-one or laya-cybersec?
bekko-system-one: Free (open weights). laya-cybersec: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, bekko-system-one or laya-cybersec?
By their publishers’ figures, bekko-system-one answers in about 5 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 bekko-system-one or laya-cybersec locally?
Yes, both: systemone pull hotchpotch/bekko-system-one and systemone pull textcortex/laya-cybersec download the weights.
5 ms
95.4 ms
p95 latency
5.4 ms
149 ms
Evaluation suite
The maker's short-input speed probe (4-option Choice, RTX 5090, 1 Oct 2026)
TextCortex saved run: 279 single-window inputs, PyTorch batch one
