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.
A 396M ModernBERT-large cross-encoder that answers typed questions about a text or a JSON state: one or several options, scores, yes/no with "not stated", spans with evidence quotes, rankings and numeric bins, each with a confidence and an act-or-escalate signal.
Decides
choice, classify, route
choice, score, noul, rank, extract
Architecture
nativ
solvi
Fine-tuned from
dicta-il/neodictabert
answerdotai/modernbert-large
License
cc-by-4.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
96.2%
59.4%
Calibration error
0.010
0.210
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 solvi?
nativ-he-decision is from Yoav Pinto and solvi from solvi. Both have open weights you can download and run. Both answer choice questions. Only nativ-he-decision answers classify and route. Only solvi answers score, noul, rank and extract. nativ-he-decision reads up to 1K tokens of state, against 512 tokens for solvi. nativ-he-decision is the smaller model, at 364M parameters to 396M. nativ-he-decision is licensed cc-by-4.0; solvi, apache-2.0.
Which is more accurate, nativ-he-decision or solvi?
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), solvi 59.4% on Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, nativ-he-decision or solvi?
nativ-he-decision: Free (open weights). solvi: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run nativ-he-decision or solvi locally?
Yes, both: systemone pull yoav-pinto/nativ-he-decision and systemone pull solvi-ai/solvi download the weights.
Evaluation suite
nativ-bench user-intent task, 4 options (MASSIVE Hebrew, 2,973 items; the maker's own suite)
Fast Decisions public dev split (100 rows x 17 domains, macro), the maker's own harness, zero-shot
