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.
Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
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 mira?
decision is from vLLM Semantic Router and mira from SAGEA. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions.
Which is more accurate, decision or mira?
They report on different suites — decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted), mira 61.3% on s1-decision-bench — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decision or mira?
decision: Free (open weights). mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision or mira locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull sagea/mira download the weights.
