A multimodal decision classifier over text, image, audio and video on Gemma 4 12B, fine-tuned on 30,000 questions. Returns a probability per option and generates nothing.
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, noul, score, classify
choice, score, noul, classify
Architecture
jev-omni
von
Fine-tuned from
google/gemma-4-12b-it
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.6%
63.9%
Calibration error
0.040
0.045
Valid action rate
—
—
Median latency
83 ms
18 ms
p95 latency
—
—
Evaluation suite
DecisionBench Medium (author's set)
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 jev-omni and von?
jev-omni is from akhilaaa3 and von from wfzyx. Both have open weights you can download and run. Both answer choice, noul, score and classify questions. von is the smaller model, at 395M parameters to 12B.
Which is more accurate, jev-omni or von?
They report on different suites — jev-omni 87.6% on DecisionBench Medium (author's set), 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, jev-omni or von?
jev-omni: Free (open weights). von: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, jev-omni or von?
By their publishers’ figures, von answers in about 18 ms at the median and jev-omni in about 83 ms — measured on different hardware, so treat it as a rough guide.
Can I run jev-omni or von locally?
Yes, both: systemone pull akhilaaa3/jev-omni and systemone pull wfzyx/von download the weights.
