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.
Invergent's decision model for text and images. A fine-tune of Gemma-4-26B-A4B (about 4B parameters active per token) that answers Choice, Noul and Score questions, with an optional thinking mode for harder questions.
Decides
choice
choice, score, noul, classify, route
Architecture
cua-s1
rune
Fine-tuned from
—
google/gemma-4-26b-a4b-it
License
mit
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Invergent
Input price
—
—
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 rune?
cua-s1-forms is from Cua and rune from Surogate (Invergent). cua-s1-forms has open weights you can download and run; rune has open weights and a hosted API. Both answer choice questions. Only rune answers score, noul, classify and route. cua-s1-forms is the smaller model, at 706K parameters to 26B. cua-s1-forms is licensed mit; rune, apache-2.0.
Which is more accurate, cua-s1-forms or rune?
Only cua-s1-forms publishes an accuracy figure (100.0% on 196-decision evaluation on real forms); rune does not, so there is no comparison to make without your own test.
Which is cheaper, cua-s1-forms or rune?
cua-s1-forms: Free (open weights). rune: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or rune locally?
Yes, both: systemone pull cua/cua-s1-forms and systemone pull surogate/rune download the weights.
