A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
A Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul, classify, route
choice, route, classify
Architecture
julia
trio-spark
Fine-tuned from
jhu-clsp/mmbert-small
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
MachineFi
Input price
—
$0.042/MTok
Decision accuracy
73.2%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Evaluation suite
typed-decisions test set (400 cases, 2,000 questions)
—
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 julia-1 and trio-spark-v1?
julia-1 is from Supersonic Labs and trio-spark-v1 from MachineFi. julia-1 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 julia-1 answers score and noul. julia-1 reads up to 8K tokens of state, against 1K tokens for trio-spark-v1. julia-1 is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, julia-1 or trio-spark-v1?
Only julia-1 publishes an accuracy figure (73.2% on typed-decisions test set (400 cases, 2,000 questions)); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, julia-1 or trio-spark-v1?
julia-1: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run julia-1 or trio-spark-v1 locally?
julia-1 yes — systemone pull supersonic-labs/julia-1 downloads its weights. The other is only served as a hosted API.
