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.
StartLux's decision family in six sizes, 0.8B to a 35B-A3B mixture of experts. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server. Text, JSON or images, up to 256K tokens.
Decides
choice, noul, route, classify
choice, score, noul
Architecture
decisiontune
startlux-decision
Fine-tuned from
answerdotai/modernbert-large
—
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
88.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
26 ms
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 startlux-decision?
decisiontune is from DecisionTune and startlux-decision from StartLux. Both have open weights you can download and run. Both answer choice and noul questions. Only decisiontune answers route and classify. Only startlux-decision answers score. startlux-decision reads up to 256K tokens of state, against 8K tokens for decisiontune. decisiontune is the smaller model, at 395M parameters to 4.7B. decisiontune is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Which is more accurate, decisiontune or startlux-decision?
Only startlux-decision publishes an accuracy figure (88.3% on JevBench public set (231 items; 204 correct), maker's run); decisiontune does not, so there is no comparison to make without your own test.
Which is cheaper, decisiontune or startlux-decision?
decisiontune: Free (open weights). startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decisiontune or startlux-decision locally?
Yes, both: systemone pull decision-tune/decisiontune and systemone pull startlux/startlux-decision download the weights.
—
—
Evaluation suite
—
JevBench public set (231 items; 204 correct), maker's run
