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.
Metask Lab's calibrated decision model in 16 languages. Qwen3.5-4B with a merged LoRA trained with the Nimble candidate-logit objective; one forward pass and a softmax over at most 26 answer-letter logits, with one temperature per question type.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
decision
metask-jev
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%
80.1%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
62.8 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 metask-jev?
decision is from vLLM Semantic Router and metask-jev from Metask Lab. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decision reads up to 16K tokens of state, against 4K tokens for metask-jev. metask-jev is the smaller model, at 4.5B parameters to 9.0B.
Which is more accurate, decision or metask-jev?
They report on different suites — decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted), metask-jev 80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decision or metask-jev?
decision: Free (open weights). metask-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decision or metask-jev locally?
Yes, both: systemone pull vllm-semantic-router/decision and systemone pull metask-lab/metask-jev download the weights.
