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.
An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
cygnet
laya
Fine-tuned from
google/gemma-4-12b-it
answerdotai/modernbert-large
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.9%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
50 ms
39.5 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 laya?
cygnet is from Blockbrain Labs and laya from Convai Innovations. Both have open weights you can download and run. Both answer choice, score and noul questions. Only laya answers classify and route. cygnet reads up to 16K tokens of state, against 512 tokens for laya. laya is the smaller model, at 421M parameters to 12B. cygnet is licensed mit; laya, apache-2.0.
Which is more accurate, cygnet or laya?
Only cygnet publishes an accuracy figure (87.9% on JevBench public set (231 items), JevBench CLI); laya does not, so there is no comparison to make without your own test.
Which is cheaper, cygnet or laya?
cygnet: Free (open weights). laya: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, cygnet or laya?
By their publishers’ figures, laya answers in about 39.5 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 laya locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull convai-innovations/laya download the weights.
