The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.
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.
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 decision and jev-omni?
decision is from vLLM Semantic Router and jev-omni from akhilaaa3. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only decision answers route. decision is the smaller model, at 9.0B parameters to 12B.
Which is more accurate, decision or jev-omni?
They report on different suites — decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted), jev-omni 87.6% on DecisionBench Medium (author's set) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decision or jev-omni?
decision: Free (open weights). jev-omni: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision or jev-omni locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull akhilaaa3/jev-omni download the weights.
