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 typed-decision layer for Google's DiffusionGemma, from David Villalón at Maisa AI. It compiles a request into a small answer canvas, runs one denoising read on patched vLLM and reads the probabilities of the allowed labels, for text, images and images offered as options.
Decides
choice
choice, score, noul
Architecture
cua-s1
djev
Fine-tuned from
—
google/diffusiongemma-26b-a4b-it
License
mit
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Maisa
Input price
—
$0.035/MTok
Decision accuracy
100.0%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Evaluation suite
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 djev?
cua-s1-forms is from Cua and djev from Maisa. cua-s1-forms has open weights you can download and run; djev has open weights and a hosted API. Both answer choice questions. Only djev answers score and noul. cua-s1-forms is the smaller model, at 706K parameters to 26B. cua-s1-forms is licensed mit; djev, apache-2.0.
Which is more accurate, cua-s1-forms or djev?
Only cua-s1-forms publishes an accuracy figure (100.0% on 196-decision evaluation on real forms); djev does not, so there is no comparison to make without your own test.
Which is cheaper, cua-s1-forms or djev?
cua-s1-forms: Free (open weights). djev: $0.035 / $0 per 1M, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or djev locally?
Yes, both: systemone pull cua/cua-s1-forms and systemone pull maisa/djev download the weights.
