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 embedding model turned decision model. Qwen3-Embedding-4B with a merged LoRA, driven by the open JevEmbed toolkit, which scores Choice, Score and Noul questions from embedding similarity and returns a distribution without generating text.
Decides
choice, score, noul
choice, score, noul, classify
Architecture
cygnet
jevembed
Fine-tuned from
google/gemma-4-12b-it
qwen/qwen3-embedding-4b
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.9%
85.9%
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 jevembed?
cygnet is from Blockbrain Labs and jevembed from HIT-TMG (Lychee Team). Both have open weights you can download and run. Both answer choice, score and noul questions. Only jevembed answers classify. cygnet reads up to 16K tokens of state, against 1K tokens for jevembed. jevembed is the smaller model, at 4.0B parameters to 12B. cygnet is licensed mit; jevembed, apache-2.0.
Which is more accurate, cygnet or jevembed?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, jevembed 85.9% on JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or jevembed?
cygnet: Free (open weights). jevembed: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run cygnet or jevembed locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull hit-tmg/jevembed download the weights.
Evaluation suite
JevBench public set (231 items), JevBench CLI
JevEmbed-Data test split (64,110 hard-label questions), final LoRA checkpoint before merging
