A 2.8 MB byte-level transformer for GUI form filling. For each form element it returns one probability per typed option (fill an entity, check, click or skip), using jevlike's option-attention head.
A ModernBERT-large encoder with an option-marker head. Premise and options are packed into one sequence and each option's marker is scored in a single bidirectional pass; version 1.2 makes the scoring order-invariant.
Decides
choice
choice, score, noul, classify
Architecture
cua-s1
von
Fine-tuned from
—
answerdotai/modernbert-large
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
100.0%
63.9%
Calibration error
—
0.045
Valid action rate
—
—
Median latency
—
18 ms
p95 latency
—
—
Evaluation suite
196-decision evaluation on real forms
JevBench public standard tier
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 cua-s1-forms and von?
cua-s1-forms is from Cua and von from wfzyx. Both have open weights you can download and run. Both answer choice questions. Only von answers score, noul and classify. cua-s1-forms is the smaller model, at 706K parameters to 395M. cua-s1-forms is licensed mit; von, apache-2.0.
Which is more accurate, cua-s1-forms or von?
They report on different suites — cua-s1-forms 100.0% on 196-decision evaluation on real forms, von 63.9% on JevBench public standard tier — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cua-s1-forms or von?
cua-s1-forms: Free (open weights). von: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or von locally?
Yes, both: systemone pull cua/cua-s1-forms and systemone pull wfzyx/von download the weights.
