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 Thai-and-English System One model. Qwen3.5-0.8B continued-pretrained on about 5B Thai tokens, its language-model head replaced by a 256-way slot head (slot 255 abstains), trained on 2–3M decision examples and temperature-calibrated per question type.
Decides
choice
choice, score, noul, classify, route
Architecture
cua-s1
openthai
Fine-tuned from
—
qwen/qwen3.5-0.8b-base
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
100.0%
74.3%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
40 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 cua-s1-forms and openthai-systemone?
cua-s1-forms is from Cua and openthai-systemone from iApp Technology. Both have open weights you can download and run. Both answer choice questions. Only openthai-systemone answers score, noul, classify and route. cua-s1-forms is the smaller model, at 706K parameters to 800M. cua-s1-forms is licensed mit; openthai-systemone, apache-2.0.
Which is more accurate, cua-s1-forms or openthai-systemone?
They report on different suites — cua-s1-forms 100.0% on 196-decision evaluation on real forms, openthai-systemone 74.3% on Bespoke public subsets (13, macro average) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cua-s1-forms or openthai-systemone?
cua-s1-forms: Free (open weights). openthai-systemone: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or openthai-systemone locally?
Yes, both: systemone pull cua/cua-s1-forms and systemone pull iapp-technology/openthai-systemone download the weights.
