FrontiersMind's decision model on a base it pre-trained from scratch. Each question reads the state and its own tokens once and a 256-dimension pointer head scores the options; Choice and Score take up to 255 entries, and nothing is generated.
A Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul
choice, route, classify
Architecture
lumma-fev
trio-spark
Fine-tuned from
frontiersmind/lumma-0.6b-base
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
MachineFi
Input price
—
$0.042/MTok
Decision accuracy
64.0%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
45.8 ms
—
p95 latency
—
—
Evaluation suite
typed-decisions (maker's table; split not stated)
—
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 lumma-fev and trio-spark-v1?
lumma-fev is from FrontiersMind and trio-spark-v1 from MachineFi. lumma-fev has open weights you can download and run; trio-spark-v1 is only available as a hosted API. Both answer choice questions. Only lumma-fev answers score and noul. Only trio-spark-v1 answers route and classify. lumma-fev reads up to 8K tokens of state, against 1K tokens for trio-spark-v1. lumma-fev is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, lumma-fev or trio-spark-v1?
Only lumma-fev publishes an accuracy figure (64.0% on typed-decisions (maker's table; split not stated)); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, lumma-fev or trio-spark-v1?
lumma-fev: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run lumma-fev or trio-spark-v1 locally?
lumma-fev yes — systemone pull frontiersmind/lumma-fev downloads its weights. The other is only served as a hosted API.
