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.
Together AI's Jev-style classifier. A LoRA fine-tune of Qwen3.5-4B that reads a state, a question and 2 to 24 options and returns one option letter. Served on Together's platform; recipe published.
Decides
choice, noul, score, classify
choice, classify, route
Architecture
jev-omni
tev
Fine-tuned from
google/gemma-4-12b-it
qwen/qwen3.5-4b
License
apache-2.0
Unspecified — weights licence being finalised
Availability
Open weights
Open weights + hosted API
Hosted by
—
Together AI
Input price
—
$0.042/MTok
Decision accuracy
87.6%
88.0%
Calibration error
0.040
—
Valid action rate
—
—
Median latency
83 ms
—
p95 latency
—
—
Evaluation suite
DecisionBench Medium (author's set)
Together development set (reused, not held out)
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 tev1?
jev-omni is from akhilaaa3 and tev1 from Together AI. jev-omni has open weights you can download and run; tev1 has open weights and a hosted API. Both answer choice and classify questions. Only jev-omni answers noul and score. Only tev1 answers route. tev1 is the smaller model, at 4.0B parameters to 12B. jev-omni is licensed apache-2.0; tev1, other.
Which is more accurate, jev-omni or tev1?
They report on different suites — jev-omni 87.6% on DecisionBench Medium (author's set), tev1 88.0% on Together development set (reused, not held out) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, jev-omni or tev1?
jev-omni: Free (open weights). tev1: $0.042 / $0 per 1M, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run jev-omni or tev1 locally?
Yes, both: systemone pull akhilaaa3/jev-omni and systemone pull together-ai/tev1 download the weights.
