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 rank-16 LoRA on Qwen3.5-4B built for the JevBench setting. A document, a policy and a question go in; a calibrated distribution over the option letters comes out of one forward pass. Research and demo use only.
Decides
choice, score, noul, classify, route
choice, score, noul, classify
Architecture
decision
hopper
Fine-tuned from
qwen/qwen3.5-9b
qwen/qwen3.5-4b
License
apache-2.0
Research and demo use only (training data includes RACE, non-commercial); serving code Apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.4%
68.5%
Calibration error
—
0.102
Valid action rate
—
—
Median latency
—
—
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 hopper?
decision is from vLLM Semantic Router and hopper from HopitAI. Both have open weights you can download and run. Both answer choice, score, noul and classify questions. Only decision answers route. hopper is the smaller model, at 4.0B parameters to 9.0B. decision is licensed apache-2.0; hopper, other.
Which is more accurate, decision or hopper?
They report on different suites — decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted), hopper 68.5% on JevBench public hard tier (111 items, measured by the authors) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decision or hopper?
decision: Free (open weights). hopper: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision or hopper locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull hopit-ai/hopper download the weights.
