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.
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, noul, score, classify
choice, score, noul, classify
Architecture
jev-omni
open-jev
Fine-tuned from
google/gemma-4-12b-it
microsoft/deberta-v3-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.6%
85.4%
Calibration error
0.040
0.022
Valid action rate
—
—
Median latency
83 ms
28 ms
p95 latency
—
—
Evaluation suite
DecisionBench Medium (author's set)
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 open-jev-deberta-v3-large?
jev-omni is from akhilaaa3 and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer choice, noul, score and classify questions. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 12B.
Which is more accurate, jev-omni or open-jev-deberta-v3-large?
They report on different suites — jev-omni 87.6% on DecisionBench Medium (author's set), 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, jev-omni or open-jev-deberta-v3-large?
jev-omni: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, jev-omni or open-jev-deberta-v3-large?
By their publishers’ figures, open-jev-deberta-v3-large answers in about 28 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 open-jev-deberta-v3-large locally?
Yes, both: systemone pull akhilaaa3/jev-omni and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
