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.
Upstage's structured decision model, a System One endpoint on Solar Mini 4. Returns a choice, a score or a yes/no answer with a probability read from the model, in one forward pass, on the same /v1/systemone schema as Jev.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
cygnet
solar
Fine-tuned from
google/gemma-4-12b-it
—
License
mit
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Upstage
Input price
—
$0.10/MTok
Decision accuracy
87.9%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
50 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 cygnet and solar-decide?
cygnet is from Blockbrain Labs and solar-decide from Upstage. cygnet has open weights you can download and run; solar-decide is only available as a hosted API. Both answer choice, score and noul questions. Only solar-decide answers classify and route. solar-decide reads up to 512K tokens of state, against 16K tokens for cygnet. cygnet is licensed mit; solar-decide, proprietary.
Which is more accurate, cygnet or solar-decide?
Only cygnet publishes an accuracy figure (87.9% on JevBench public set (231 items), JevBench CLI); solar-decide does not, so there is no comparison to make without your own test.
Which is cheaper, cygnet or solar-decide?
cygnet: Free (open weights). solar-decide: $0.1 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run cygnet or solar-decide locally?
cygnet yes — systemone pull blockbrain-labs/cygnet downloads its weights. The other is only served as a hosted API.
