A training-free layer that turns an open LLM into a decision model. It reads typed choice, yes/no and score answers from one prefill, removes option-order bias with no labels and, from a few hundred labels, calibrates or fits a closed-form head. Weights stay untouched.
A multimodal decision classifier over text, image, audio and video on Gemma 4 12B, fine-tuned on 30,000 questions. Returns a probability per option and generates nothing.
Decides
choice, score, noul, classify, route
choice, noul, score, classify
Architecture
anyjev
jev-omni
Fine-tuned from
qwen/qwen3-8b
google/gemma-4-12b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
87.6%
Calibration error
0.034
0.040
Valid action rate
—
—
Median latency
—
83 ms
p95 latency
—
—
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
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 anyjev and jev-omni?
anyjev is from Nokia Applied Research and jev-omni from akhilaaa3. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only anyjev answers route. anyjev is the smaller model, at 8.0B parameters to 12B.
Which is more accurate, anyjev or jev-omni?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, jev-omni 87.6% on DecisionBench Medium (author's set) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or jev-omni?
anyjev: Free (open weights). jev-omni: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or jev-omni locally?
Yes, both: systemone pull nokia-applied-research/anyjev and systemone pull akhilaaa3/jev-omni download the weights.
