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 Situated World Model for fast judgment in agent loops.
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 trio-spark-v1?
decision is from vLLM Semantic Router and trio-spark-v1 from MachineFi. decision has open weights you can download and run; trio-spark-v1 is only available as a hosted API. Both answer choice, classify and route questions. Only decision answers score and noul. decision reads up to 16K tokens of state, against 1K tokens for trio-spark-v1. decision is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, decision or trio-spark-v1?
Only decision publishes an accuracy figure (77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted)); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, decision or trio-spark-v1?
decision: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run decision or trio-spark-v1 locally?
decision yes — systemone pull vllm-semantic-router/decision downloads its weights. The other is only served as a hosted API.
