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 149.6M ModernBERT-base cross-encoder with a scalar head that picks an agent's next action or tool from labels and descriptions you supply. Each option is scored against the state and a softmax ranks the set; no text is generated. Experimental preview, not calibrated.
Decides
choice, score, noul, classify, route
choice, rank, route
Architecture
anyjev
modernjev
Fine-tuned from
qwen/qwen3-8b
answerdotai/modernbert-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
73.4%
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 modernjev-decide?
anyjev is from Nokia and modernjev-decide from Maziyar Panahi. Both have open weights you can download and run. Both answer choice and route questions. Only anyjev answers score, noul and classify. Only modernjev-decide answers rank. modernjev-decide is the smaller model, at 150M parameters to 8.0B.
Which is more accurate, anyjev or modernjev-decide?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, modernjev-decide 73.4% on AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or modernjev-decide?
anyjev: Free (open weights). modernjev-decide: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or modernjev-decide locally?
Yes, both: systemone pull nokia/anyjev and systemone pull maziyar-panahi/modernjev-decide download the weights.
—
Evaluation suite
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
AgentToolDecisions-180K held-out test, next action type (1,158 decisions, 3 choices; the maker's split)
