An independent Jev-shaped reproduction on DeBERTa-v3-large. One state and any number of choice, score and yes/no questions go in, and a calibrated distribution per question comes out of one forward pass. Public gold labels only.
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
choice, score, noul, classify, route
Architecture
open-jev
security-one
Fine-tuned from
microsoft/deberta-v3-large
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
85.4%
99.8%
Calibration error
0.022
—
Valid action rate
—
—
Median latency
28 ms
—
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 open-jev-deberta-v3-large and security-one?
open-jev-deberta-v3-large is from Kotoba Labs and security-one from Superagent. open-jev-deberta-v3-large has open weights you can download and run; security-one has open weights and a hosted API. Both answer choice, score, noul and classify questions. Only security-one answers route. security-one reads up to 256K tokens of state, against 512 tokens for open-jev-deberta-v3-large. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 27B.
Which is more accurate, open-jev-deberta-v3-large or security-one?
They report on different suites — open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ), 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, open-jev-deberta-v3-large or security-one?
open-jev-deberta-v3-large: 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 open-jev-deberta-v3-large or security-one locally?
Yes, both: systemone pull kotoba-labs/open-jev-deberta-v3-large and systemone pull superagent/security-one download the weights.
Evaluation suite
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
