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.
AutoTrust's student of TypeSafe Jev 1.13. A frozen Qwen3.8-27B plus a 108.9M-parameter decision block trained on Jev's own output distributions; one set of weights answers typed questions in one pass (System 1) or generates text with the untouched base (System 2).
Decides
choice
choice, score, noul
Architecture
cua-s1
blocks-of-experts
Fine-tuned from
—
qwen/qwen3.8-27b
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
100.0%
88.7%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
137 ms
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 jev-27b?
cua-s1-forms is from Cua and jev-27b from AutoTrust AI Lab. Both have open weights you can download and run. Both answer choice questions. Only jev-27b answers score and noul. cua-s1-forms is the smaller model, at 706K parameters to 27B. cua-s1-forms is licensed mit; jev-27b, apache-2.0.
Which is more accurate, cua-s1-forms or jev-27b?
They report on different suites — cua-s1-forms 100.0% on 196-decision evaluation on real forms, jev-27b 88.7% on JevBench public set (231 items), family-macro score, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cua-s1-forms or jev-27b?
cua-s1-forms: Free (open weights). jev-27b: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or jev-27b locally?
Yes, both: systemone pull cua/cua-s1-forms and systemone pull autotrust-ai/jev-27b download the weights.
196-decision evaluation on real forms
JevBench public set (231 items), family-macro score, maker's run
