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.
TokenRhythm's prefill-only decision model for agent workflows. Built on its NeoHorse-1-4B (a Qwen3.5-4B derivative), it predicts Choice, Noul and Score answers over application-defined options without generating text, with optional single-image input.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
cygnet
neohorse
Fine-tuned from
google/gemma-4-12b-it
tokenrhythm/neohorse-1-4b
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.9%
75.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
50 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 neohorse-jev?
cygnet is from Blockbrain Labs and neohorse-jev from TokenRhythm. Both have open weights you can download and run. Both answer choice, score and noul questions. Only neohorse-jev answers classify and route. neohorse-jev is the smaller model, at 4.0B parameters to 12B. cygnet is licensed mit; neohorse-jev, apache-2.0.
Which is more accurate, cygnet or neohorse-jev?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, neohorse-jev 75.3% on JevBench public set (231 items), vLLM, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or neohorse-jev?
cygnet: Free (open weights). neohorse-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run cygnet or neohorse-jev locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull tokenrhythm/neohorse-jev download the weights.
—
Evaluation suite
JevBench public set (231 items), JevBench CLI
JevBench public set (231 items), vLLM, maker's run
