The first System One model. Reads a state, answers typed Choice, Score and Noul questions in one call with calibrated probabilities, and generates no text. Closed weights, served by TypeSafe AI.
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.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
jev
lumma-fev
Fine-tuned from
—
frontiersmind/lumma-0.6b-base
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
TypeSafe AI
—
Input price
$0.042/MTok
—
Decision accuracy
—
64.0%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
45.8 ms
p95 latency
—
—
Evaluation suite
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 jev and lumma-fev?
jev is from TypeSafe AI and lumma-fev from FrontiersMind. jev is only available as a hosted API; lumma-fev has open weights you can download and run. Both answer choice, score and noul questions. Only jev answers classify and route. jev reads up to 32K tokens of state, against 8K tokens for lumma-fev. jev is licensed proprietary; lumma-fev, apache-2.0.
Which is more accurate, jev or lumma-fev?
Only lumma-fev publishes an accuracy figure (64.0% on typed-decisions (maker's table; split not stated)); jev does not, so there is no comparison to make without your own test.
Which is cheaper, jev or lumma-fev?
jev: $0.042 / $0 per 1M. lumma-fev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev or lumma-fev locally?
lumma-fev yes — systemone pull frontiersmind/lumma-fev downloads its weights. The other is only served as a hosted API.
