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.
One of the earliest Jev-shaped scorers. A sequence-classification head on Qwen3.5-4B-Base scores each (state, question, option) triple and softmaxes per question. Non-commercial licence.
Decides
choice, score, noul
choice, score, noul, classify
Architecture
cygnet
scorer
Fine-tuned from
google/gemma-4-12b-it
qwen/qwen3.5-4b-base
License
mit
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.9%
70.7%
Calibration error
—
0.044
Valid action rate
—
—
Median latency
50 ms
112 ms
p95 latency
—
—
Evaluation suite
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 system-one-qwen3-5-4b-scorer?
cygnet is from Blockbrain Labs and system-one-qwen3-5-4b-scorer from pngwn. Both have open weights you can download and run. Both answer choice, score and noul questions. Only system-one-qwen3-5-4b-scorer answers classify. system-one-qwen3-5-4b-scorer is the smaller model, at 4.0B parameters to 12B. cygnet is licensed mit; system-one-qwen3-5-4b-scorer, cc-by-nc-4.0.
Which is more accurate, cygnet or system-one-qwen3-5-4b-scorer?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, system-one-qwen3-5-4b-scorer 70.7% on author-reported — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or system-one-qwen3-5-4b-scorer?
cygnet: Free (open weights). system-one-qwen3-5-4b-scorer: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, cygnet or system-one-qwen3-5-4b-scorer?
By their publishers’ figures, cygnet answers in about 50 ms at the median and system-one-qwen3-5-4b-scorer in about 112 ms — measured on different hardware, so treat it as a rough guide.
Can I run cygnet or system-one-qwen3-5-4b-scorer locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull pngwn/system-one-qwen3-5-4b-scorer download the weights.
