DecisionTune's 395M decision model: ModernBERT-large fine-tuned with a 4 KB scoring head that scores a marker per option, answering a choice or yes/no question in one encoder pass with a probability for every option. Runs locally on CPU or GPU via PyTorch, MLX or ONNX.
SimpleJev's LoRA adapters and pointer head that turn an open model into a typed-decision model: given a state, a question and the options, it returns a probability for every option without generating text. This entry is the Qwen3.8-27B release; the others are linked.
Decides
choice, noul, route, classify
choice, score, noul
Architecture
decisiontune
jevany
Fine-tuned from
answerdotai/modernbert-large
qwen/qwen3.8-27b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
86.0%
Calibration error
—
0.026
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 decisiontune and jevany?
decisiontune is from DecisionTune and jevany from SimpleJev. Both have open weights you can download and run. Both answer choice and noul questions. Only decisiontune answers route and classify. Only jevany answers score. decisiontune is the smaller model, at 395M parameters to 27B.
Which is more accurate, decisiontune or jevany?
Only jevany publishes an accuracy figure (86.0% on SimpleJev Transfer suite (1,046 decisions from seven cross-domain datasets plus robustness slices; the maker's own)); decisiontune does not, so there is no comparison to make without your own test.
Which is cheaper, decisiontune or jevany?
decisiontune: Free (open weights). jevany: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decisiontune or jevany locally?
Yes, both: systemone pull decision-tune/decisiontune and systemone pull simplejev/jevany download the weights.
—
Evaluation suite
—
SimpleJev Transfer suite (1,046 decisions from seven cross-domain datasets plus robustness slices; the maker's own)
