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.
Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
Decides
choice, score, noul
choice, score, noul, classify, route
Architecture
lumma-fev
mira
Fine-tuned from
frontiersmind/lumma-0.6b-base
jhu-clsp/mmbert-small
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
64.0%
74.5%
Calibration error
—
0.025
Valid action rate
—
100.0%
Median latency
45.8 ms
30 ms
p95 latency
—
43 ms
Evaluation suite
typed-decisions (maker's table; split not stated)
s1-decision-bench
Latest version
2026.09
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 mira?
lumma-fev is from FrontiersMind and mira from SAGEA. Both have open weights you can download and run. Both answer choice, score and noul questions. Only mira answers classify and route.
Which is more accurate, lumma-fev or mira?
They report on different suites — lumma-fev 64.0% on typed-decisions (maker's table; split not stated), mira 74.5% on s1-decision-bench — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, lumma-fev or mira?
lumma-fev: Free (open weights). mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, lumma-fev or mira?
By their publishers’ figures, mira answers in about 30 ms at the median and lumma-fev in about 45.8 ms — measured on different hardware, so treat it as a rough guide.
Can I run lumma-fev or mira locally?
Yes, both: systemone pull frontiersmind/lumma-fev and systemone pull sagea/mira download the weights.