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.
The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
anyjev
decision
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3.5-9b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
77.4%
Calibration error
0.034
—
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 decision?
anyjev is from Nokia Applied Research and decision from vLLM Semantic Router. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. anyjev is the smaller model, at 8.0B parameters to 9.0B.
Which is more accurate, anyjev or decision?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or decision?
anyjev: Free (open weights). decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or decision locally?
Yes, both: systemone pull nokia-applied-research/anyjev and systemone pull vllm-semantic-router/decision download the weights.
—
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
