A 364M Hebrew decision encoder on NeoDictaBERT: give it a state, a question and 2 to 7 free-text options and it returns a probability for each option in one forward pass, about 70 ms on a laptop CPU. Hebrew 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, classify, route
choice, score, noul, classify, route
Architecture
nativ
security-one
Fine-tuned from
dicta-il/neodictabert
denis-pplx/autojev-27b
License
cc-by-4.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Superagent
Input price
—
—
Decision accuracy
96.2%
99.8%
Calibration error
0.010
—
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 nativ-he-decision and security-one?
nativ-he-decision is from Yoav Pinto and security-one from Superagent. nativ-he-decision has open weights you can download and run; security-one has open weights and a hosted API. Both answer choice, classify and route questions. Only security-one answers score and noul. security-one reads up to 256K tokens of state, against 1K tokens for nativ-he-decision. nativ-he-decision is the smaller model, at 364M parameters to 27B. nativ-he-decision is licensed cc-by-4.0; security-one, apache-2.0.
Which is more accurate, nativ-he-decision or security-one?
They report on different suites — nativ-he-decision 96.2% on nativ-bench user-intent task, 4 options (MASSIVE Hebrew, 2,973 items; the maker's own suite), 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, nativ-he-decision or security-one?
nativ-he-decision: 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 nativ-he-decision or security-one locally?
Yes, both: systemone pull yoav-pinto/nativ-he-decision and systemone pull superagent/security-one download the weights.
Evaluation suite
nativ-bench user-intent task, 4 options (MASSIVE Hebrew, 2,973 items; the maker's own suite)
