HEAD TO HEAD

canopy-jev vs security-one

Q: Can I run canopy-jev or security-one locally?

Yes, both: systemone pull camellia86/canopy-jev and systemone pull superagent/security-one download the weights.

Ruoxi Qiu: canopy-jev and Superagent: security-one, compared on what they decide, where they run, what they cost and what their publishers report.

The short version

canopy-jev has open weights you can download and run; security-one has open weights and a hosted API.
Both answer choice, noul and score questions.
Only security-one answers classify and route.

Property	camellia86/canopy-jev	superagent/security-one
Summary	Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens.	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, noul, score	choice, score, noul, classify, route
Architecture	canopy-jev	security-one
Fine-tuned from	qwen/qwen3.8-27b	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	87.4%	99.8%
Calibration error	—	—
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 canopy-jev and security-one?

canopy-jev is from Ruoxi Qiu and security-one from Superagent. canopy-jev has open weights you can download and run; security-one has open weights and a hosted API. Both answer choice, noul and score questions. Only security-one answers classify and route.

Which is more accurate, canopy-jev or security-one?

They report on different suites — canopy-jev 87.4% on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer, 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, canopy-jev or security-one?

canopy-jev: 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 canopy-jev or security-one locally?

Yes, both: systemone pull camellia86/canopy-jev and systemone pull superagent/security-one download the weights.

Evaluation suite	JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer	BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70)