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.
Metask Lab's calibrated decision model in 16 languages. Qwen3.5-4B with a merged LoRA trained with the Nimble candidate-logit objective; one forward pass and a softmax over at most 26 answer-letter logits, with one temperature per question type.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
cygnet
metask-jev
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%
80.1%
Calibration error
—
—
Valid action rate
—
—
Median latency
50 ms
62.8 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 metask-jev?
cygnet is from Blockbrain Labs and metask-jev from Metask Lab. Both have open weights you can download and run. Both answer choice, score and noul questions. Only metask-jev answers classify and route. cygnet reads up to 16K tokens of state, against 4K tokens for metask-jev. metask-jev is the smaller model, at 4.5B parameters to 12B. cygnet is licensed mit; metask-jev, apache-2.0.
Which is more accurate, cygnet or metask-jev?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, metask-jev 80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or metask-jev?
cygnet: Free (open weights). metask-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, cygnet or metask-jev?
By their publishers’ figures, cygnet answers in about 50 ms at the median and metask-jev in about 62.8 ms — measured on different hardware, so treat it as a rough guide.
Can I run cygnet or metask-jev locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull metask-lab/metask-jev download the weights.
Evaluation suite
JevBench public set (231 items), JevBench CLI
JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run
