Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.
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.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
jevk5
open-jev
Fine-tuned from
qwen/qwen3.5-4b
microsoft/deberta-v3-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
78.4%
85.4%
Calibration error
0.035
0.022
Valid action rate
—
—
Median latency
13.2 ms
28 ms
p95 latency
—
—
Evaluation suite
JevBench public hard tier
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 jevk5 and open-jev-deberta-v3-large?
jevk5 is from Alibi Serikbay and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only jevk5 answers route. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 4.0B.
Which is more accurate, jevk5 or open-jev-deberta-v3-large?
They report on different suites — jevk5 78.4% on JevBench public hard tier, open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, jevk5 or open-jev-deberta-v3-large?
jevk5: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, jevk5 or open-jev-deberta-v3-large?
By their publishers’ figures, jevk5 answers in about 13.2 ms at the median and open-jev-deberta-v3-large in about 28 ms — measured on different hardware, so treat it as a rough guide.
Can I run jevk5 or open-jev-deberta-v3-large locally?
Yes, both: systemone pull alibi-serikbay/jevk5 and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
