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.
Invergent's decision model for text and images. A fine-tune of Gemma-4-26B-A4B (about 4B parameters active per token) that answers Choice, Noul and Score questions, with an optional thinking mode for harder questions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
bosun
rune
Fine-tuned from
qwen/qwen3-1.7b
google/gemma-4-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Invergent
Input price
—
—
Decision accuracy
84.9%
—
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 rune?
bosun is from Hanno Labs and rune from Surogate (Invergent). bosun has open weights you can download and run; rune 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 26B.
Which is more accurate, bosun or rune?
Only bosun publishes an accuracy figure (84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)); rune does not, so there is no comparison to make without your own test.
Which is cheaper, bosun or rune?
bosun: Free (open weights). rune: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run bosun or rune locally?
Yes, both: systemone pull hanno-labs/bosun and systemone pull surogate/rune download the weights.
Evaluation suite
DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)
