An independent Jev-shaped reproduction on DeBERTa-v3-large. One state and any number of choice, score and yes/no questions go in, and a calibrated distribution per question comes out of one forward pass. Public gold labels only.
A Thai-and-English System One model. Qwen3.5-0.8B continued-pretrained on about 5B Thai tokens, its language-model head replaced by a 256-way slot head (slot 255 abstains), trained on 2–3M decision examples and temperature-calibrated per question type.
Decides
choice, score, noul, classify
choice, score, noul, classify, route
Architecture
open-jev
openthai
Fine-tuned from
microsoft/deberta-v3-large
qwen/qwen3.5-0.8b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
85.4%
74.3%
Calibration error
0.022
—
Valid action rate
—
—
Median latency
28 ms
40 ms
p95 latency
—
—
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 open-jev-deberta-v3-large and openthai-systemone?
open-jev-deberta-v3-large is from Kotoba Labs and openthai-systemone from iApp Technology. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only openthai-systemone answers route. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 800M.
Which is more accurate, open-jev-deberta-v3-large or openthai-systemone?
They report on different suites — open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ), openthai-systemone 74.3% on Bespoke public subsets (13, macro average) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, open-jev-deberta-v3-large or openthai-systemone?
open-jev-deberta-v3-large: Free (open weights). openthai-systemone: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, open-jev-deberta-v3-large or openthai-systemone?
By their publishers’ figures, open-jev-deberta-v3-large answers in about 28 ms at the median and openthai-systemone in about 40 ms — measured on different hardware, so treat it as a rough guide.
Can I run open-jev-deberta-v3-large or openthai-systemone locally?
Yes, both: systemone pull kotoba-labs/open-jev-deberta-v3-large and systemone pull iapp-technology/openthai-systemone download the weights.
Evaluation suite
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
