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.
One of the earliest Jev-shaped scorers. A sequence-classification head on Qwen3.5-4B-Base scores each (state, question, option) triple and softmaxes per question. Non-commercial licence.
Decides
choice, score, noul, classify
choice, score, noul, classify
Architecture
open-jev
scorer
Fine-tuned from
microsoft/deberta-v3-large
qwen/qwen3.5-4b-base
License
apache-2.0
cc-by-nc-4.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
85.4%
70.7%
Calibration error
0.022
0.044
Valid action rate
—
—
Median latency
28 ms
112 ms
p95 latency
—
—
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 system-one-qwen3-5-4b-scorer?
open-jev-deberta-v3-large is from Kotoba Labs and system-one-qwen3-5-4b-scorer from pngwn. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 4.0B. open-jev-deberta-v3-large is licensed apache-2.0; system-one-qwen3-5-4b-scorer, cc-by-nc-4.0.
Which is more accurate, open-jev-deberta-v3-large or system-one-qwen3-5-4b-scorer?
They report on different suites — open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ), system-one-qwen3-5-4b-scorer 70.7% on author-reported — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, open-jev-deberta-v3-large or system-one-qwen3-5-4b-scorer?
open-jev-deberta-v3-large: Free (open weights). system-one-qwen3-5-4b-scorer: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, open-jev-deberta-v3-large or system-one-qwen3-5-4b-scorer?
By their publishers’ figures, open-jev-deberta-v3-large answers in about 28 ms at the median and system-one-qwen3-5-4b-scorer in about 112 ms — measured on different hardware, so treat it as a rough guide.
Can I run open-jev-deberta-v3-large or system-one-qwen3-5-4b-scorer locally?
Yes, both: systemone pull kotoba-labs/open-jev-deberta-v3-large and systemone pull pngwn/system-one-qwen3-5-4b-scorer download the weights.
