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 System One model from Interfaze AI. A rank-32 LoRA on Qwen3.5-4B reads yes/no, choice and score answers from the logits of one forward pass, returns calibrated probabilities and serves the /v1/systemone API.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
cygnet
lev
Fine-tuned from
google/gemma-4-12b-it
qwen/qwen3.5-4b
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.9%
68.9%
Calibration error
—
0.115
Valid action rate
—
—
Median latency
50 ms
69 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 lev?
cygnet is from Blockbrain Labs and lev from Interfaze AI. Both have open weights you can download and run. Both answer choice, score and noul questions. Only lev answers classify and route. lev is the smaller model, at 4.0B parameters to 12B. cygnet is licensed mit; lev, apache-2.0.
Which is more accurate, cygnet or lev?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, lev 68.9% on S1Bench (13 public subsets, macro) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or lev?
cygnet: Free (open weights). lev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, cygnet or lev?
By their publishers’ figures, cygnet answers in about 50 ms at the median and lev in about 69 ms — measured on different hardware, so treat it as a rough guide.
Can I run cygnet or lev locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull interfaze-ai/lev download the weights.
