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 0.4B decision model made from the first 20 layers of Qwen3-0.6B plus a small attention head that compares options. It answers choice, noul and score questions in one pass, and choice order cannot change its answer by construction. Non-commercial licence.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
anyjev
bev-decider
Fine-tuned from
qwen/qwen3-8b
qwen/qwen3-0.6b
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
74.7%
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 bev-decider?
anyjev is from Nokia and bev-decider from Avishek Biswas. Both have open weights you can download and run. Both answer choice, score and noul questions. Only anyjev answers classify and route. bev-decider is the smaller model, at 478M parameters to 8.0B. anyjev is licensed apache-2.0; bev-decider, cc-by-nc-4.0.
Which is more accurate, anyjev or bev-decider?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, bev-decider 74.7% on avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or bev-decider?
anyjev: Free (open weights). bev-decider: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or bev-decider locally?
Yes, both: systemone pull nokia/anyjev and systemone pull avishek-biswas/bev-decider download the weights.
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own
