FrontiersMind's decision model on a base it pre-trained from scratch. Each question reads the state and its own tokens once and a 256-dimension pointer head scores the options; Choice and Score take up to 255 entries, and nothing is generated.
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.
Decides
choice, score, noul
choice, classify, route
Architecture
lumma-fev
nativ
Fine-tuned from
frontiersmind/lumma-0.6b-base
dicta-il/neodictabert
License
apache-2.0
cc-by-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
64.0%
96.2%
Calibration error
—
0.010
Valid action rate
—
—
Median latency
45.8 ms
—
p95 latency
—
—
Evaluation suite
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 lumma-fev and nativ-he-decision?
lumma-fev is from FrontiersMind and nativ-he-decision from Yoav Pinto. Both have open weights you can download and run. Both answer choice questions. Only lumma-fev answers score and noul. Only nativ-he-decision answers classify and route. lumma-fev reads up to 8K tokens of state, against 1K tokens for nativ-he-decision. nativ-he-decision is the smaller model, at 364M parameters to 649M. lumma-fev is licensed apache-2.0; nativ-he-decision, cc-by-4.0.
Which is more accurate, lumma-fev or nativ-he-decision?
They report on different suites — lumma-fev 64.0% on typed-decisions (maker's table; split not stated), nativ-he-decision 96.2% on nativ-bench user-intent task, 4 options (MASSIVE Hebrew, 2,973 items; the maker's own suite) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, lumma-fev or nativ-he-decision?
lumma-fev: Free (open weights). nativ-he-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run lumma-fev or nativ-he-decision locally?
Yes, both: systemone pull frontiersmind/lumma-fev and systemone pull yoav-pinto/nativ-he-decision download the weights.
typed-decisions (maker's table; split not stated)
nativ-bench user-intent task, 4 options (MASSIVE Hebrew, 2,973 items; the maker's own suite)
