Hanno Labs' small calibrated decision model. A LoRA on Qwen3-1.7B plus trained decision-token embeddings with stable slots, returning the full distribution over up to 255 caller-defined choices and a null slot for Choice, Score and Noul questions.
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.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
bosun
jebadiah
Fine-tuned from
qwen/qwen3-1.7b
qwen/qwen3.8-27b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
84.9%
86.6%
Calibration error
0.050
0.113
Valid action rate
—
—
Median latency
—
—
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 bosun and jebadiah?
bosun is from Hanno Labs and jebadiah from Frontier Infra. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. bosun is the smaller model, at 2.0B parameters to 27B.
Which is more accurate, bosun or jebadiah?
They report on different suites — bosun 84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families), jebadiah 86.6% on JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bosun or jebadiah?
bosun: Free (open weights). jebadiah: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bosun or jebadiah locally?
Yes, both: systemone pull hanno-labs/bosun and systemone pull frontier-infra/jebadiah download the weights.
Evaluation suite
DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)
JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier
