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.
One of the earliest Jev-shaped scorers. A sequence-classification head on Qwen3.5-4B-Base scores each (state, question, option) triple and softmaxes per question. Non-commercial licence.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
anyjev
scorer
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.5-4b-base
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
70.7%
Calibration error
0.034
0.044
Valid action rate
—
—
Median latency
—
112 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 system-one-qwen3-5-4b-scorer?
anyjev is from Nokia Applied Research and system-one-qwen3-5-4b-scorer from pngwn. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only anyjev answers route. system-one-qwen3-5-4b-scorer is the smaller model, at 4.0B parameters to 8.0B. anyjev is licensed apache-2.0; system-one-qwen3-5-4b-scorer, cc-by-nc-4.0.
Which is more accurate, anyjev or system-one-qwen3-5-4b-scorer?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, system-one-qwen3-5-4b-scorer 70.7% on author-reported — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or system-one-qwen3-5-4b-scorer?
anyjev: Free (open weights). system-one-qwen3-5-4b-scorer: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or system-one-qwen3-5-4b-scorer locally?
Yes, both: systemone pull nokia-applied-research/anyjev and systemone pull pngwn/system-one-qwen3-5-4b-scorer download the weights.
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
