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 open System One model from Interfaze AI. A rank-32 LoRA on Qwen3.5-4B reads yes/no, choice and score answers from the logits of one forward pass, returns calibrated probabilities and serves the /v1/systemone API.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
decision
lev
Fine-tuned from
qwen/qwen3.5-9b
qwen/qwen3.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
77.4%
68.9%
Calibration error
—
0.115
Valid action rate
—
—
Median latency
—
69 ms
p95 latency
—
—
Evaluation suite
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 lev?
decision is from vLLM Semantic Router and lev from Interfaze AI. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. lev is the smaller model, at 4.0B parameters to 9.0B.
Which is more accurate, decision or lev?
They report on different suites — decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted), lev 68.9% on S1Bench (13 public subsets, macro) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decision or lev?
decision: Free (open weights). lev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision or lev locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull interfaze-ai/lev download the weights.
