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.
Fastino's open-weight decision model. A DeBERTa-v3-large encoder that scores label sets supplied at runtime, answers single-label, multi-label, yes/no and ordinal questions in one pass, and extracts spans and relations.
Decides
choice, score, noul
choice, score, noul, classify, extract, route
Architecture
cygnet
gliner2
Fine-tuned from
google/gemma-4-12b-it
fastino/gliner2-large-v1
License
mit
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Fastino
Input price
—
—
Decision accuracy
87.9%
60.2%
Calibration error
—
—
Valid action rate
—
—
Median latency
50 ms
38.3 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 gliner2-5-decide?
cygnet is from Blockbrain Labs and gliner2-5-decide from Fastino Labs. cygnet has open weights you can download and run; gliner2-5-decide has open weights and a hosted API. Both answer choice, score and noul questions. Only gliner2-5-decide answers classify, extract and route. gliner2-5-decide is the smaller model, at 340M parameters to 12B. cygnet is licensed mit; gliner2-5-decide, apache-2.0.
Which is more accurate, cygnet or gliner2-5-decide?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, gliner2-5-decide 60.2% on Fastino fast-decisions suite (17 datasets) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or gliner2-5-decide?
cygnet: Free (open weights). gliner2-5-decide: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Which is faster, cygnet or gliner2-5-decide?
By their publishers’ figures, gliner2-5-decide answers in about 38.3 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 gliner2-5-decide locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull fastino-labs/gliner2-5-decide download the weights.
