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.
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, score, noul, classify, route
choice, score, noul, classify
Architecture
decision
open-jev
Fine-tuned from
qwen/qwen3.5-9b
microsoft/deberta-v3-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.4%
85.4%
Calibration error
—
0.022
Valid action rate
—
—
Median latency
—
28 ms
p95 latency
—
—
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 open-jev-deberta-v3-large?
decision is from vLLM Semantic Router and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only decision answers route. decision reads up to 16K tokens of state, against 512 tokens for open-jev-deberta-v3-large. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 9.0B.
Which is more accurate, decision or open-jev-deberta-v3-large?
They report on different suites — decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted), 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, decision or open-jev-deberta-v3-large?
decision: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision or open-jev-deberta-v3-large locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
