Typed decisions from Google's frozen Gemma-4-12B-it, with no fine-tuning. A small shim over unmodified vLLM letters the options, reads the model's own probability for each letter at one answer position and applies one calibration temperature; one output token per decision.
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.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
cygnet
standard-one
Fine-tuned from
google/gemma-4-12b-it
mistralai/ministral-3-8b-instruct-2512-bf16
License
mit
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Standard Thinking
Input price
—
—
Decision accuracy
87.9%
71.1%
Calibration error
—
—
Valid action rate
—
—
Median latency
50 ms
25.8 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 cygnet and standard-one?
cygnet is from Blockbrain Labs and standard-one from Standard Thinking. cygnet has open weights you can download and run; standard-one has open weights and a hosted API. Both answer choice, score and noul questions. Only standard-one answers classify and route. cygnet reads up to 16K tokens of state, against 8K tokens for standard-one. standard-one is the smaller model, at 8.0B parameters to 12B. cygnet is licensed mit; standard-one, apache-2.0.
Which is more accurate, cygnet or standard-one?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, standard-one 71.1% on typed-decisions suite, 400 cases / 2,000 decisions (maker's served run, v2) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or standard-one?
cygnet: Free (open weights). standard-one: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Which is faster, cygnet or standard-one?
By their publishers’ figures, standard-one answers in about 25.8 ms at the median and cygnet in about 50 ms — measured on different hardware, so treat it as a rough guide.
Can I run cygnet or standard-one locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull standard-thinking/standard-one download the weights.
