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.
A multimodal decision classifier over text, image, audio and video on Gemma 4 12B, fine-tuned on 30,000 questions. Returns a probability per option and generates nothing.
Decides
choice, score, noul
choice, noul, score, classify
Architecture
cygnet
jev-omni
Fine-tuned from
google/gemma-4-12b-it
google/gemma-4-12b-it
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.9%
87.6%
Calibration error
—
0.040
Valid action rate
—
—
Median latency
50 ms
83 ms
p95 latency
—
—
Evaluation suite
JevBench public set (231 items), JevBench CLI
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 jev-omni?
cygnet is from Blockbrain Labs and jev-omni from akhilaaa3. Both have open weights you can download and run. Both answer choice, score and noul questions. Only jev-omni answers classify. cygnet is licensed mit; jev-omni, apache-2.0.
Which is more accurate, cygnet or jev-omni?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, jev-omni 87.6% on DecisionBench Medium (author's set) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or jev-omni?
cygnet: Free (open weights). jev-omni: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, cygnet or jev-omni?
By their publishers’ figures, cygnet answers in about 50 ms at the median and jev-omni in about 83 ms — measured on different hardware, so treat it as a rough guide.
Can I run cygnet or jev-omni locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull akhilaaa3/jev-omni download the weights.
