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.
Shanghai AI Laboratory's multimodal decision model. A fine-tune of Qwen3.5-4B's language backbone (vision tower frozen) that answers up to 16 Choice, Score and Noul questions about a state and up to eight images in one forward pass, with a fitted calibration temperature.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
cygnet
intern-decision
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%
80.6%
Calibration error
—
—
Valid action rate
—
—
Median latency
50 ms
44 ms
p95 latency
—
44.6 ms
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 intern-decision?
cygnet is from Blockbrain Labs and intern-decision from InternLM (Shanghai AI Laboratory). Both have open weights you can download and run. Both answer choice, score and noul questions. Only intern-decision answers classify and route. cygnet reads up to 16K tokens of state, against 8K tokens for intern-decision. intern-decision is the smaller model, at 4.5B parameters to 12B. cygnet is licensed mit; intern-decision, apache-2.0.
Which is more accurate, cygnet or intern-decision?
They report on different suites — cygnet 87.9% on JevBench public set (231 items), JevBench CLI, intern-decision 80.6% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cygnet or intern-decision?
cygnet: Free (open weights). intern-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, cygnet or intern-decision?
By their publishers’ figures, intern-decision answers in about 44 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 intern-decision locally?
Yes, both: systemone pull blockbrain-labs/cygnet and systemone pull internlm/intern-decision download the weights.
Evaluation suite
JevBench public set (231 items), JevBench CLI
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)
