AutoTrust's student of TypeSafe Jev 1.13. A frozen Qwen3.8-27B plus a 108.9M-parameter decision block trained on Jev's own output distributions; one set of weights answers typed questions in one pass (System 1) or generates text with the untouched base (System 2).
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
choice, score, noul
Architecture
blocks-of-experts
lumma-fev
Fine-tuned from
qwen/qwen3.8-27b
frontiersmind/lumma-0.6b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
88.7%
64.0%
Calibration error
—
—
Valid action rate
—
—
Median latency
137 ms
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 jev-27b and lumma-fev?
jev-27b is from AutoTrust AI Lab and lumma-fev from FrontiersMind. Both have open weights you can download and run. Both answer choice, score and noul questions. lumma-fev is the smaller model, at 649M parameters to 27B.
Which is more accurate, jev-27b or lumma-fev?
They report on different suites — jev-27b 88.7% on JevBench public set (231 items), family-macro score, maker's run, lumma-fev 64.0% on typed-decisions (maker's table; split not stated) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, jev-27b or lumma-fev?
jev-27b: Free (open weights). lumma-fev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, jev-27b or lumma-fev?
By their publishers’ figures, lumma-fev answers in about 45.8 ms at the median and jev-27b in about 137 ms — measured on different hardware, so treat it as a rough guide.
Can I run jev-27b or lumma-fev locally?
Yes, both: systemone pull autotrust-ai/jev-27b and systemone pull frontiersmind/lumma-fev download the weights.
Evaluation suite
JevBench public set (231 items), family-macro score, maker's run
