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.
FLock.io's typed-decision model, fine-tuned from Mapika's decider-2b. Reads one hidden state per question and scores the declared options, so an answer outside the list cannot occur; several questions about one state share a forward pass.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
anyjev
this-that
Fine-tuned from
qwen/qwen3-8b
mapika/decider
License
apache-2.0
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.1%
87.8%
Calibration error
0.034
—
Valid action rate
—
—
Median latency
—
31.4 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 this-that-model?
anyjev is from Nokia and this-that-model from FLock.io. Both have open weights you can download and run. Both answer choice, score and noul questions. Only anyjev answers classify and route. this-that-model is the smaller model, at 1.9B parameters to 8.0B. anyjev is licensed apache-2.0; this-that-model, mit.
Which is more accurate, anyjev or this-that-model?
They report on different suites — anyjev 77.1% on LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question, this-that-model 87.8% on limberc/this-that-complex-decisions (1,710 questions, FLock's benchmark) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, anyjev or this-that-model?
anyjev: Free (open weights). this-that-model: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run anyjev or this-that-model locally?
Yes, both: systemone pull nokia/anyjev and systemone pull flock-io/this-that-model download the weights.
LocalLLaMA/typed-decisions (2,000 held-out decisions), L2 with 300 labels per question
