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.
TokenRhythm's prefill-only decision model for agent workflows. Built on its NeoHorse-1-4B (a Qwen3.5-4B derivative), it predicts Choice, Noul and Score answers over application-defined options without generating text, with optional single-image input.
Decides
choice, classify, route
choice, score, noul, classify, route
Architecture
nativ
neohorse
Fine-tuned from
dicta-il/neodictabert
tokenrhythm/neohorse-1-4b
License
cc-by-4.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
96.2%
75.3%
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 neohorse-jev?
nativ-he-decision is from Yoav Pinto and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice, classify and route questions. Only neohorse-jev answers score and noul. nativ-he-decision is the smaller model, at 364M parameters to 4.0B. nativ-he-decision is licensed cc-by-4.0; neohorse-jev, apache-2.0.
Which is more accurate, nativ-he-decision or neohorse-jev?
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), neohorse-jev 75.3% on JevBench public set (231 items), vLLM, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, nativ-he-decision or neohorse-jev?
nativ-he-decision: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run nativ-he-decision or neohorse-jev locally?
Yes, both: systemone pull yoav-pinto/nativ-he-decision and systemone pull tokenrhythm/neohorse-jev download the weights.
Evaluation suite
nativ-bench user-intent task, 4 options (MASSIVE Hebrew, 2,973 items; the maker's own suite)
JevBench public set (231 items), vLLM, maker's run
