Frontier Infra's open decision model. A LoRA merged into Qwen3.8-27B (thinking off) that answers one typed question per forward pass with a probability over the option labels, served through AINode's TypeSafe-compatible /v1/systemone.
A Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul, classify, route
choice, route, classify
Architecture
jebadiah
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
86.6%
—
Calibration error
0.113
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Evaluation suite
JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier
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 jebadiah and trio-spark-v1?
jebadiah is from Frontier Infra and trio-spark-v1 from MachineFi. jebadiah has open weights you can download and run; trio-spark-v1 is only available as a hosted API. Both answer choice, classify and route questions. Only jebadiah answers score and noul. jebadiah is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, jebadiah or trio-spark-v1?
Only jebadiah publishes an accuracy figure (86.6% on JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, jebadiah or trio-spark-v1?
jebadiah: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run jebadiah or trio-spark-v1 locally?
jebadiah yes — systemone pull frontier-infra/jebadiah downloads its weights. The other is only served as a hosted API.
