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.
meraGPT's hosted decision model (state-decider-1). Answers yes/no, choice and rubric-score questions over one state as calibrated distributions in a single pass, on the System One schema, so the typesafe-sdk works by changing its base URL.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
bosun
state-decider
Fine-tuned from
qwen/qwen3-1.7b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
meraGPT
Input price
—
$0.030/MTok
Decision accuracy
84.9%
76.8%
Calibration error
0.050
—
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 state-decider-1?
bosun is from Hanno Labs and state-decider-1 from meraGPT. bosun has open weights you can download and run; state-decider-1 is only available as a hosted API. Both answer choice, score, noul, classify and route questions. bosun is licensed apache-2.0; state-decider-1, proprietary.
Which is more accurate, bosun or state-decider-1?
They report on different suites — bosun 84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families), state-decider-1 76.8% on typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bosun or state-decider-1?
bosun: Free (open weights). state-decider-1: $0.03 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run bosun or state-decider-1 locally?
bosun yes — systemone pull hanno-labs/bosun downloads its weights. The other is only served as a hosted API.
Evaluation suite
DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)
typed-decisions benchmark (400 cases, 2,000 decisions; teacher-ensemble references), single run
