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.
One of the earliest Jev-shaped scorers. A sequence-classification head on Qwen3.5-4B-Base scores each (state, question, option) triple and softmaxes per question. Non-commercial licence.
Decides
choice
choice, score, noul, classify
Architecture
cua-s1
scorer
Fine-tuned from
—
qwen/qwen3.5-4b-base
License
mit
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
100.0%
70.7%
Calibration error
—
0.044
Valid action rate
—
—
Median latency
—
112 ms
p95 latency
—
—
Evaluation suite
196-decision evaluation on real forms
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 system-one-qwen3-5-4b-scorer?
cua-s1-forms is from Cua and system-one-qwen3-5-4b-scorer from pngwn. Both have open weights you can download and run. Both answer choice questions. Only system-one-qwen3-5-4b-scorer answers score, noul and classify. cua-s1-forms is the smaller model, at 706K parameters to 4.0B. cua-s1-forms is licensed mit; system-one-qwen3-5-4b-scorer, cc-by-nc-4.0.
Which is more accurate, cua-s1-forms or system-one-qwen3-5-4b-scorer?
They report on different suites — cua-s1-forms 100.0% on 196-decision evaluation on real forms, system-one-qwen3-5-4b-scorer 70.7% on author-reported — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cua-s1-forms or system-one-qwen3-5-4b-scorer?
cua-s1-forms: Free (open weights). system-one-qwen3-5-4b-scorer: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or system-one-qwen3-5-4b-scorer locally?
Yes, both: systemone pull cua/cua-s1-forms and systemone pull pngwn/system-one-qwen3-5-4b-scorer download the weights.
