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).
A Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul
choice, route, classify
Architecture
blocks-of-experts
trio-spark
Fine-tuned from
qwen/qwen3.8-27b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
MachineFi
Input price
—
$0.042/MTok
Decision accuracy
88.7%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
137 ms
—
p95 latency
—
—
Evaluation suite
JevBench public set (231 items), family-macro score, maker's run
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 trio-spark-v1?
jev-27b is from AutoTrust AI Lab and trio-spark-v1 from MachineFi. jev-27b has open weights you can download and run; trio-spark-v1 is only available as a hosted API. Both answer choice questions. Only jev-27b answers score and noul. Only trio-spark-v1 answers route and classify. jev-27b is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, jev-27b or trio-spark-v1?
Only jev-27b publishes an accuracy figure (88.7% on JevBench public set (231 items), family-macro score, maker's run); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, jev-27b or trio-spark-v1?
jev-27b: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run jev-27b or trio-spark-v1 locally?
jev-27b yes — systemone pull autotrust-ai/jev-27b downloads its weights. The other is only served as a hosted API.
