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 rank-16 LoRA on Qwen3.5-4B built for the JevBench setting. A document, a policy and a question go in; a calibrated distribution over the option letters comes out of one forward pass. Research and demo use only.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
anyjev
hopper
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.5-4b
License
apache-2.0
Research and demo use only (training data includes RACE, non-commercial); serving code Apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
68.5%
Calibration error
0.034
0.102
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 anyjev and hopper?
anyjev is from Nokia Applied Research and hopper from HopitAI. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only anyjev answers route. hopper is the smaller model, at 4.0B parameters to 8.0B. anyjev is licensed apache-2.0; hopper, other.
Which is more accurate, anyjev or hopper?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, hopper 68.5% on JevBench public hard tier (111 items, measured by the authors) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or hopper?
anyjev: Free (open weights). hopper: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or hopper locally?
Yes, both: systemone pull nokia-applied-research/anyjev and systemone pull hopit-ai/hopper download the weights.
—
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
JevBench public hard tier (111 items, measured by the authors)
