HEAD TO HEAD

gutsy vs security-one

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

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

Omar (kouhxp): gutsy and Superagent: security-one, compared on what they decide, where they run, what they cost and what their publishers report.

The short version

gutsy 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.
security-one reads up to 256K tokens of state, against 8K tokens for gutsy.
gutsy is the smaller model, at 800M parameters to 27B.

Property	kouhxp/gutsy	superagent/security-one
Summary	Omar (kouhxp)'s CPU decision model: a Qwen3.5-0.8B fine-tune shipped as GGUF for llama.cpp that answers yes/no, choice and score questions with a probability per option plus a 'none of these' reject probability, served by a local Jev-style HTTP runtime.	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	gutsy	security-one
Fine-tuned from	qwen/qwen3.5-0.8b	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	73.2%	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 gutsy and security-one?

gutsy is from Omar (kouhxp) and security-one from Superagent. gutsy 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. security-one reads up to 256K tokens of state, against 8K tokens for gutsy. gutsy is the smaller model, at 800M parameters to 27B.

Which is more accurate, gutsy or security-one?

They report on different suites — gutsy 73.2% on JevBench public set (231 items; 169 correct), the maker's own run with Q8_0, 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, gutsy or security-one?

gutsy: 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 gutsy or security-one locally?

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

Evaluation suite	JevBench public set (231 items; 169 correct), the maker's own run with Q8_0	BIPIA binary prompt-injection detector adaptation (800 rows; Superagent's frozen evaluation, unsafe if P(unsafe) >= 0.70)