A family of open System One models by Mark Marosi, decider-0.8b, decider-2b, decider-4b and decider-35b-a3b on Qwen3.5 bases, that softmax letter logits at an answer slot. This page carries decider-2b v11.
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 decider and trio-spark-v1?
decider is from Mapika and trio-spark-v1 from MachineFi. decider 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 decider answers score and noul. decider reads up to 32K tokens of state, against 1K tokens for trio-spark-v1. decider is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, decider or trio-spark-v1?
Only decider publishes an accuracy figure (75.2% on Decider regression set, 28 held-out tasks (decider-2b v11)); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, decider or trio-spark-v1?
decider: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run decider or trio-spark-v1 locally?
decider yes — systemone pull mapika/decider downloads its weights. The other is only served as a hosted API.
