Berget AI's System One model for gating agent commands: a LoRA adapter and a fine-tuned joint schema head on Cloudflare's Clef-Flash that answer noul, choice and score questions over a state in one forward pass. Trained on Swedish and English operations decisions.
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
noul, choice, score
choice, score, noul, classify, route
Architecture
clef
security-one
Fine-tuned from
cloudflare/clef-flash
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
97.0%
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 bev and security-one?
bev is from Berget AI and security-one from Superagent. bev has open weights you can download and run; security-one has open weights and a hosted API. Both answer noul, choice and score questions. Only security-one answers classify and route. bev is the smaller model, at 9.0B parameters to 27B.
Which is more accurate, bev or security-one?
They report on different suites — bev 97.0% on Berget held-out risk split (16,902 questions; same operations-traffic corpora as training), 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, bev or security-one?
bev: 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 bev or security-one locally?
Yes, both: systemone pull berget-ai/bev and systemone pull superagent/security-one download the weights.
—
Evaluation suite
Berget held-out risk split (16,902 questions; same operations-traffic corpora as training)
