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.
Standard Thinking's decision model. Ministral 3 8B with a merged LoRA, served through stock SGLang and an open jev-adapter that exposes /v1/systemone and scores the supplied options in one forward pass with per-type temperatures.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
bosun
standard-one
Fine-tuned from
qwen/qwen3-1.7b
mistralai/ministral-3-8b-instruct-2512-bf16
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Standard Thinking
Input price
—
—
Decision accuracy
84.9%
71.1%
Calibration error
0.050
—
Valid action rate
—
—
Median latency
—
25.8 ms
p95 latency
—
41.9 ms
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 standard-one?
bosun is from Hanno Labs and standard-one from Standard Thinking. bosun has open weights you can download and run; standard-one has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. bosun is the smaller model, at 2.0B parameters to 8.0B.
Which is more accurate, bosun or standard-one?
They report on different suites — bosun 84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families), standard-one 71.1% on typed-decisions suite, 400 cases / 2,000 decisions (maker's served run, v2) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bosun or standard-one?
bosun: Free (open weights). standard-one: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run bosun or standard-one locally?
Yes, both: systemone pull hanno-labs/bosun and systemone pull standard-thinking/standard-one download the weights.
Evaluation suite
DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)
