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.
A ModernBERT-large encoder with an option-marker head. Premise and options are packed into one sequence and each option's marker is scored in a single bidirectional pass; version 1.2 makes the scoring order-invariant.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
jevk5
von
Fine-tuned from
qwen/qwen3.5-4b
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
78.4%
63.9%
Calibration error
0.035
0.045
Valid action rate
—
—
Median latency
13.2 ms
18 ms
p95 latency
—
—
Evaluation suite
JevBench public hard tier
JevBench public standard 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 von?
jevk5 is from Alibi Serikbay and von from wfzyx. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only jevk5 answers route. von is the smaller model, at 395M parameters to 4.0B.
Which is more accurate, jevk5 or von?
They report on different suites — jevk5 78.4% on JevBench public hard tier, von 63.9% on JevBench public standard tier — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, jevk5 or von?
jevk5: Free (open weights). von: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, jevk5 or von?
By their publishers’ figures, jevk5 answers in about 13.2 ms at the median and von in about 18 ms — measured on different hardware, so treat it as a rough guide.
Can I run jevk5 or von locally?
Yes, both: systemone pull alibi-serikbay/jevk5 and systemone pull wfzyx/von download the weights.