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.
meraGPT's hosted decision model (state-decider-1). Answers yes/no, choice and rubric-score questions over one state as calibrated distributions in a single pass, on the System One schema, so the typesafe-sdk works by changing its base URL.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
lumma-fev
state-decider
Fine-tuned from
frontiersmind/lumma-0.6b-base
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
64.0%
76.8%
Calibration error
—
—
Valid action rate
—
—
Median latency
45.8 ms
—
p95 latency
—
—
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 state-decider-1?
lumma-fev is from FrontiersMind and state-decider-1 from meraGPT. lumma-fev has open weights you can download and run; state-decider-1 is only available as a hosted API. Both answer choice, score and noul questions. Only state-decider-1 answers classify and route. lumma-fev reads up to 8K tokens of state, against 4K tokens for state-decider-1. lumma-fev is licensed apache-2.0; state-decider-1, proprietary.
Which is more accurate, lumma-fev or state-decider-1?
They report on different suites — lumma-fev 64.0% on typed-decisions (maker's table; split not stated), state-decider-1 76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, lumma-fev or state-decider-1?
lumma-fev: Free (open weights). state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run lumma-fev or state-decider-1 locally?
lumma-fev yes — systemone pull frontiersmind/lumma-fev downloads its weights. The other is only served as a hosted API.
Evaluation suite
typed-decisions (maker's table; split not stated)
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
