HEAD TO HEAD

anyjev vs security-one

Q: Can I run anyjev or security-one locally?

Yes, both: systemone pull nokia/anyjev and systemone pull superagent/security-one download the weights.

Nokia: anyjev and Superagent: security-one, compared on what they decide, where they run, what they cost and what their publishers report.

The short version

anyjev has open weights you can download and run; security-one has open weights and a hosted API.
Both answer choice, score, noul, classify and route questions.
anyjev is the smaller model, at 8.0B parameters to 27B.

Property	nokia/anyjev	superagent/security-one
Summary	A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.	Superagent's 27B security decision model. It scores 2 to 16 supplied options in one forward pass and returns a probability for each, for triaging prompt injection, agent tool calls, code changes, logs and alerts. Apache-2.0 weights (gated, auto-approved) plus a hosted API.
Decides	choice, score, noul, classify, route	choice, score, noul, classify, route
Architecture	anyjev	security-one
Fine-tuned from	qwen/qwen3-8b	denis-pplx/autojev-27b
License	apache-2.0	apache-2.0
Availability	Open weights	Open weights + hosted API
Hosted by	—	Superagent
Input price	—	—
Decision accuracy	77.1%	99.8%
Calibration error	0.034	—
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 anyjev and security-one?

anyjev is from Nokia and security-one from Superagent. anyjev has open weights you can download and run; security-one has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. anyjev is the smaller model, at 8.0B parameters to 27B.

Which is more accurate, anyjev or security-one?

They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, security-one 99.8% on BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70) — so the numbers do not rank them. Test both on your own labelled examples.

Which is cheaper, anyjev or security-one?

anyjev: Free (open weights). security-one: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.

Can I run anyjev or security-one locally?

Yes, both: systemone pull nokia/anyjev and systemone pull superagent/security-one download the weights.

Evaluation suite	LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question	BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70)