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.
Metask Lab's calibrated decision model in 16 languages. Qwen3.5-4B with a merged LoRA trained with the Nimble candidate-logit objective; one forward pass and a softmax over at most 26 answer-letter logits, with one temperature per question type.
Decides
choice
choice, score, noul, classify, route
Architecture
cua-s1
metask-jev
Fine-tuned from
—
qwen/qwen3.5-4b
License
mit
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
100.0%
80.1%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
62.8 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 metask-jev?
cua-s1-forms is from Cua and metask-jev from Metask Lab. Both have open weights you can download and run. Both answer choice questions. Only metask-jev answers score, noul, classify and route. cua-s1-forms is the smaller model, at 706K parameters to 4.5B. cua-s1-forms is licensed mit; metask-jev, apache-2.0.
Which is more accurate, cua-s1-forms or metask-jev?
They report on different suites — cua-s1-forms 100.0% on 196-decision evaluation on real forms, metask-jev 80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, cua-s1-forms or metask-jev?
cua-s1-forms: Free (open weights). metask-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run cua-s1-forms or metask-jev locally?
Yes, both: systemone pull cua/cua-s1-forms and systemone pull metask-lab/metask-jev download the weights.
196-decision evaluation on real forms
JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run
