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 ModernBERT-large encoder with an option-marker head. Premise and options are packed into one sequence and each option's marker is scored in a single bidirectional pass; version 1.2 makes the scoring order-invariant.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
anyjev
von
Fine-tuned from
qwen/qwen3-8b
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
63.9%
Calibration error
0.034
0.045
Valid action rate
—
—
Median latency
—
18 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 anyjev and von?
anyjev is from Nokia Applied Research and von from wfzyx. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only anyjev answers route. von is the smaller model, at 395M parameters to 8.0B.
Which is more accurate, anyjev or von?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, von 63.9% on JevBench public standard tier — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or von?
anyjev: Free (open weights). von: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or von locally?
Yes, both: systemone pull nokia-applied-research/anyjev and systemone pull wfzyx/von download the weights.
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
