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.
Juspay's open decision model. Qwen3.6-35B-A3B with a merged rank-16 LoRA, shipped with a pinned SGLang serving bundle that answers Choice, Score and Noul questions over text, images or a video through a TypeSafe-compatible /v1/systemone API.
Decides
choice, score, noul, classify
choice, score, noul, classify, route
Architecture
open-jev
xor
Fine-tuned from
microsoft/deberta-v3-large
qwen/qwen3.6-35b-a3b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
85.4%
90.0%
Calibration error
0.022
0.073
Valid action rate
—
—
Median latency
28 ms
69 ms
p95 latency
—
162 ms
Evaluation suite
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
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 xor?
open-jev-deberta-v3-large is from Kotoba Labs and xor from Juspay. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only xor answers route. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 35B.
Which is more accurate, open-jev-deberta-v3-large or xor?
They report on different suites — open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ), xor 90.0% on JevBench public set (231 items), maker's self-run of Xor 1.2 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, open-jev-deberta-v3-large or xor?
open-jev-deberta-v3-large: Free (open weights). xor: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, open-jev-deberta-v3-large or xor?
By their publishers’ figures, open-jev-deberta-v3-large answers in about 28 ms at the median and xor in about 69 ms — measured on different hardware, so treat it as a rough guide.
Can I run open-jev-deberta-v3-large or xor locally?
Yes, both: systemone pull kotoba-labs/open-jev-deberta-v3-large and systemone pull juspay/xor download the weights.
JevBench public set (231 items), maker's self-run of Xor 1.2
