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.
Featherless AI's open server that turns a stock Hugging Face language model into a typed-decision endpoint. It reads the next-token logits for each question and builds the Choice, Score or Noul answer itself; no classifier head is trained and no JSON is generated.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
cygnet
simple-jev
Fine-tuned from
google/gemma-4-12b-it
google/gemma-4-26b-a4b-it
License
mit
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Featherless AI
Input price
—
—
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 simple-jev?
cygnet is from Blockbrain Labs and simple-jev from Featherless AI. cygnet has open weights you can download and run; simple-jev has open weights and a hosted API. Both answer choice, score and noul questions. Only simple-jev answers classify and route. cygnet is licensed mit; simple-jev, apache-2.0.
Which is more accurate, cygnet or simple-jev?
Only cygnet publishes an accuracy figure (87.9% on JevBench public set (231 items), JevBench CLI); simple-jev does not, so there is no comparison to make without your own test.
Which is cheaper, cygnet or simple-jev?
cygnet: Free (open weights). simple-jev: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run cygnet or simple-jev locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull featherless-ai/simple-jev download the weights.
