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.
meraGPT's hosted decision model (state-decider-1). Answers yes/no, choice and rubric-score questions over one state as calibrated distributions in a single pass, on the System One schema, so the typesafe-sdk works by changing its base URL.
Decides
choice
choice, score, noul, classify, route
Architecture
cua-s1
state-decider
Fine-tuned from
—
—
License
mit
proprietary
Availability
Open weights
Hosted API
Hosted by
—
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
100.0%
76.8%
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 state-decider-1?
cua-s1-forms is from Cua and state-decider-1 from meraGPT. cua-s1-forms has open weights you can download and run; state-decider-1 is only available as a hosted API. Both answer choice questions. Only state-decider-1 answers score, noul, classify and route. cua-s1-forms is licensed mit; state-decider-1, proprietary.
Which is more accurate, cua-s1-forms or state-decider-1?
They report on different suites — cua-s1-forms 100.0% on 196-decision evaluation on real forms, state-decider-1 76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cua-s1-forms or state-decider-1?
cua-s1-forms: Free (open weights). state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or state-decider-1 locally?
cua-s1-forms yes — systemone pull cua/cua-s1-forms downloads its weights. The other is only served as a hosted API.
196-decision evaluation on real forms
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
