Standard Thinking's decision model. Ministral 3 8B with a merged LoRA, served through stock SGLang and an open jev-adapter that exposes /v1/systemone and scores the supplied options in one forward pass with per-type temperatures.
StartLux's decision family in five sizes, 0.8B to 27B. All questions in a request are answered in one forward pass, with a probability for every option, through a TypeSafe /v1/systemone-compatible server that records CUDA graphs for short requests.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
standard-one
startlux-decision
Fine-tuned from
mistralai/ministral-3-8b-instruct-2512-bf16
—
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights + hosted API
Open weights
Hosted by
Standard Thinking
—
Input price
—
—
Decision accuracy
71.1%
88.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
25.8 ms
26 ms
p95 latency
41.9 ms
—
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 standard-one and startlux-decision?
standard-one is from Standard Thinking and startlux-decision from StartLux. standard-one has open weights and a hosted API; startlux-decision has open weights you can download and run. Both answer choice, score and noul questions. Only standard-one answers classify and route. startlux-decision is the smaller model, at 4.7B parameters to 8.0B. standard-one is licensed apache-2.0; startlux-decision, cc-by-nc-4.0.
Which is more accurate, standard-one or startlux-decision?
They report on different suites — standard-one 71.1% on typed-decisions suite, 400 cases / 2,000 decisions (maker's served run, v2), startlux-decision 88.3% on JevBench public set (231 items; 204 correct), maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, standard-one or startlux-decision?
standard-one: Hosted, price not published, or free to self-host. startlux-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, standard-one or startlux-decision?
By their publishers’ figures, standard-one answers in about 25.8 ms at the median and startlux-decision in about 26 ms — measured on different hardware, so treat it as a rough guide.
Can I run standard-one or startlux-decision locally?
Yes, both: systemone pull standard-thinking/standard-one and systemone pull startlux/startlux-decision download the weights.
