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.
FLock.io's typed-decision model, fine-tuned from Mapika's decider-2b. Reads one hidden state per question and scores the declared options, so an answer outside the list cannot occur; several questions about one state share a forward pass.
Decides
choice, score, noul
choice, score, noul
Architecture
cygnet
this-that
Fine-tuned from
google/gemma-4-12b-it
mapika/decider
License
mit
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.9%
87.8%
Calibration error
—
—
Valid action rate
—
—
Median latency
50 ms
31.4 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 this-that-model?
cygnet is from Blockbrain Labs and this-that-model from FLock.io. Both have open weights you can download and run. Both answer choice, score and noul questions. this-that-model is the smaller model, at 1.9B parameters to 12B.
Which is more accurate, cygnet or this-that-model?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, this-that-model 87.8% on limberc/this-that-complex-decisions (1,710 questions, FLock's benchmark) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or this-that-model?
cygnet: Free (open weights). this-that-model: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, cygnet or this-that-model?
By their publishers’ figures, this-that-model answers in about 31.4 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 this-that-model locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull flock-io/this-that-model download the weights.
